bump: version 0.1.2 → 0.1.3 [skip ci]

.gitignore

@@ -2,5 +2,6 @@
 /tmp
 /.env
 !cli/**
-/.idea/
+.idea/
 /loki.iml
+/.idea/

.idea/.gitignore

@@ -1,10 +0,0 @@
-# Default ignored files
-/shelf/
-/workspace.xml
-# Editor-based HTTP Client requests
-/httpRequests/
-# Datasource local storage ignored files
-/dataSources/
-/dataSources.local.xml
-# Zeppelin ignored files
-/ZeppelinRemoteNotebooks/

CHANGELOG.md

@@ -1,3 +1,15 @@
+## v0.1.3 (2025-12-13)
+
+### Feat
+
+- Improved MCP implementation to minimize the tokens needed to utilize it so it doesn't quickly overwhelm the token space for a given model
+
+## v0.1.2 (2025-11-08)
+
+### Refactor
+
+- Gave the GitHub MCP server a default placeholder value that doesn't require the vault
+
 ## v0.1.1 (2025-11-08)
 
 ## v0.1.0 (2025-11-07)

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "loki-ai"
-version = "0.1.1"
+version = "0.1.3"
 edition = "2024"
 authors = ["Alex Clarke <alex.j.tusa@gmail.com>"]
 description = "An all-in-one, batteries included LLM CLI Tool"

README.md

@@ -19,7 +19,6 @@ Coming from [AIChat](https://github.com/sigoden/aichat)? Follow the [migration g
 
 ## Quick Links
 * [AIChat Migration Guide](./docs/AICHAT-MIGRATION.md): Coming from AIChat? Follow the migration guide to get started.
-* [History](#history): A history of how Loki came to be.
 * [Installation](#install): Install Loki
 * [Getting Started](#getting-started): Get started with Loki by doing first-run setup steps.
 * [REPL](./docs/REPL.md): Interactive Read-Eval-Print Loop for conversational interactions with LLMs and Loki.
@@ -41,21 +40,7 @@ Coming from [AIChat](https://github.com/sigoden/aichat)? Follow the [migration g
 * [Client Configurations](./docs/clients/CLIENTS.md): Configuration instructions for various LLM providers.
     * [Patching API Requests](./docs/clients/PATCHES.md): Learn how to patch API requests for advanced customization.
 * [Custom Themes](./docs/THEMES.md): Change the look and feel of Loki to your preferences with custom themes.
-
+* [History](#history): A history of how Loki came to be.
----
-
-## History
-Loki originally started as a fork of the fantastic [AIChat CLI](https://github.com/sigoden/aichat). The purpose was to 
-simply fix a bug in how MCP servers worked with AIChat so that I could specify different ones for agents. However, it 
-has since evolved far beyond that and become a passion project with a life of its own!
-
-Loki now has first class MCP server support (with support for local and remote servers alike), a built-in vault for 
-interpolating secrets in configuration files, built-in agents, built-in macros, dynamic tab completions, integrated
-custom functions (no `argc` dependency), improved documentation, and much more with many more plans for the future!
-
-The original kudos goes out to all the developers of the wonderful AIChat project!
-
----
 
 ## Prerequisites
 Loki requires the following tools to be installed on your system:
@@ -164,21 +149,6 @@ guide you through the process when you first attempt to access the vault. So, to
 loki --list-secrets
 ```
 
-### First Time Setup
-In order for Loki to function correctly, you'll need to add a few secrets to the Loki vault so the MCP servers can
-function.
-
-**GitHub MCP Server:**
-* `GITHUB_PERSONAL_ACCESS_TOKEN` - A GitHub Personal Access Token with `repo` and `workflow` scopes.
-  See [Creating a GitHub Personal Access Token](https://docs.github.com/en/authentication/keeping-your-account-and-data-secure/managing-your-personal-access-tokens)
-
-#### Add the secrets to the Loki vault
-You can add the secrets to the Loki vault using the following commands (First time use will prompt you to create a vault 
-password file):
-```sh
-loki --add-secret GITHUB_PERSONAL_ACCESS_TOKEN
-```
-
 ### Tab-Completions
 You can also enable tab completions to make using Loki easier. To do so, add the following to your shell profile:
 ```shell
@@ -272,5 +242,20 @@ The appearance of Loki can be modified using the following settings:
 | `user_agent`         | `null`        | The name of the `User-Agent` that should be passed in the `User-Agent` header on all requests to model providers |
 | `save_shell_history` | `true`        | Enables or disables REPL command history                                                                         |
 
+---
+
+## History
+Loki originally started as a fork of the fantastic [AIChat CLI](https://github.com/sigoden/aichat). The purpose was to 
+simply fix a bug in how MCP servers worked with AIChat so that I could specify different ones for agents. However, it 
+has since evolved far beyond that and become a passion project with a life of its own!
+
+Loki now has first class MCP server support (with support for local and remote servers alike), a built-in vault for 
+interpolating secrets in configuration files, built-in agents, built-in macros, dynamic tab completions, integrated
+custom functions (no `argc` dependency), improved documentation, and much more with many more plans for the future!
+
+The original kudos goes out to all the developers of the wonderful AIChat project!
+
+---
+
 ## Creator
 * [Alex Clarke](https://github.com/Dark-Alex-17)

assets/functions/mcp.json

@@ -11,21 +11,12 @@
         "ghcr.io/github/github-mcp-server"
       ],
       "env": {
-        "GITHUB_PERSONAL_ACCESS_TOKEN": "{{GITHUB_PERSONAL_ACCESS_TOKEN}}"
+        "GITHUB_PERSONAL_ACCESS_TOKEN": "YOUR_GITHUB_TOKEN"
       }
     },
     "docker": {
       "command": "uvx",
       "args": ["mcp-server-docker"]
-    },
-    "slack": {
-      "command": "npx",
-      "args": ["-y", "slack-mcp-server@latest", "--transport", "stdio"],
-      "env": {
-        "SLACK_MCP_XOXC_TOKEN": "{{SLACK_MCP_XOXC_TOKEN}}",
-        "SLACK_MCP_XOXD_TOKEN": "{{SLACK_MCP_XOXD_TOKEN}}",
-        "SLACK_MCP_ADD_MESSAGE_TOOL": true
-      }
     }
   }
 }

docs/AICHAT-MIGRATION.md

@@ -3,8 +3,8 @@ Loki originally started as a fork of AIChat but has since evolved into its own s
 
 As a result, there's some changes you'll need to make to your AIChat configuration to be able to use Loki.
 
-Be sure you've followed the [first-time setup steps](../README.md#first-time-setup) so that the Loki configuration 
+Be sure you've run `loki` at least once so that the Loki configuration directory and subdirectories exist and is
-directory and subdirectories exist and is populated with the built-in defaults.
+populated with the built-in defaults.
 
 ## Global Configuration File
 You should be able to copy/paste your AIChat configuration file into your Loki configuration directory. Since the 

docs/ENVIRONMENT-VARIABLES.md

@@ -84,7 +84,7 @@ You can also customize the location of full agent configurations using the follo
 
 | Environment Variable         | Description                                                                                                                         |
 |------------------------------|-------------------------------------------------------------------------------------------------------------------------------------|
-| `<AGENT_NAME>_CONFIG_FILE    | Customize the location of the agent's configuration file; e.g. `SQL_CONFIG_FILE`                                                    |
+| `<AGENT_NAME>_CONFIG_FILE`   | Customize the location of the agent's configuration file; e.g. `SQL_CONFIG_FILE`                                                    |
 | `<AGENT_NAME>_MODEL`         | Customize the `model` used for the agent; e.g `SQL_MODEL`                                                                           |
 | `<AGENT_NAME>_TEMPERATURE`   | Customize the `temperature` used for the agent; e.g. `SQL_TEMPERATURE`                                                              |
 | `<AGENT_NAME>_TOP_P`         | Customize the `top_p` used for the agent; e.g. `SQL_TOP_P`                                                                          |

docs/VAULT.md

@@ -114,7 +114,7 @@ At the time of writing, the following files support Loki secret injection:
 |-------------------------|-----------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------|
 | `config.yaml`           | The main Loki configuration file  | Cannot use secret injection on the `vault_password_file` field                                                                            |
 | `functions/mcp.json`    | The MCP server configuration file |                                                                                                                                           |
-| `<agent>/tools.<py/sh>` | Tool files for agents             | Specific configuration and only supported for Agents, not all global tools ([see below](#environment-variable-secret-injection-in-agents) |
+| `<agent>/tools.<py/sh>` | Tool files for agents             | Specific configuration and only supported for Agents, not all global tools ([see below](#environment-variable-secret-injection-in-agents)) |
 
 
 Note that all paths are relative to the Loki configuration directory. The directory varies by system, so you can find yours by

docs/function-calling/MCP-SERVERS.md

@@ -83,9 +83,7 @@ enabled_mcp_servers: null        # Which MCP servers to enable by default (e.g.
 ```
 
 A special note about `enabled_mcp_servers`: a user can set this to `all` to enable all configured MCP servers in the 
-`functions/mcp.json` configuration. However, **this should be used with caution**. When there is a significant number 
+`functions/mcp.json` configuration.
-of configured MCP servers, enabling all MCP servers may overwhelm the context length of a model, and quickly exceed 
-token limits.
 
 (See the [Configuration Example](../../config.example.yaml) file for an example global configuration with all options.)
 

models.yaml

@@ -3,6 +3,20 @@
 #  - https://platform.openai.com/docs/api-reference/chat
 - provider: openai
   models:
+    - name: gpt-5.1
+      max_input_tokens: 400000
+      max_output_tokens: 128000
+      input_price: 1.25
+      output_price: 10
+      supports_vision: true
+      supports_function_calling: true
+    - name: gpt-5.1-chat-latest
+      max_input_tokens: 400000
+      max_output_tokens: 128000
+      input_price: 1.25
+      output_price: 10
+      supports_vision: true
+      supports_function_calling: true
     - name: gpt-5
       max_input_tokens: 400000
       max_output_tokens: 128000
@@ -31,13 +45,6 @@
       output_price: 0.4
       supports_vision: true
       supports_function_calling: true
-    - name: gpt-5-codex
-      max_input_tokens: 400000
-      max_output_tokens: 128000
-      input_price: 1.25
-      output_price: 10
-      supports_vision: true
-      supports_function_calling: true
     - name: gpt-4.1
       max_input_tokens: 1047576
       max_output_tokens: 32768
@@ -259,6 +266,30 @@
           thinking:
             type: enabled
             budget_tokens: 16000
+    - name: claude-haiku-4-5-20251001
+      max_input_tokens: 200000
+      max_output_tokens: 8192
+      require_max_tokens: true
+      input_price: 1
+      output_price: 5
+      supports_vision: true
+      supports_function_calling: true
+    - name: claude-haiku-4-5-20251001:thinking
+      real_name: claude-haiku-4-5-20251001
+      max_input_tokens: 200000
+      max_output_tokens: 24000
+      require_max_tokens: true
+      input_price: 1
+      output_price: 5
+      supports_vision: true
+      supports_function_calling: true
+      patch:
+        body:
+          temperature: null
+          top_p: null
+          thinking:
+            type: enabled
+            budget_tokens: 16000
     - name: claude-opus-4-1-20250805
       max_input_tokens: 200000
       max_output_tokens: 8192
@@ -660,6 +691,29 @@
           thinking:
             type: enabled
             budget_tokens: 16000
+    - name: claude-haiku-4-5@20251001
+      max_input_tokens: 200000
+      max_output_tokens: 8192
+      require_max_tokens: true
+      input_price: 1
+      output_price: 5
+      supports_vision: true
+      supports_function_calling: true
+    - name: claude-haiku-4-5@20251001:thinking
+      real_name: claude-haiku-4-5@20251001
+      max_input_tokens: 200000
+      max_output_tokens: 24000
+      require_max_tokens: true
+      input_price: 1
+      output_price: 5
+      supports_vision: true
+      patch:
+        body:
+          temperature: null
+          top_p: null
+          thinking:
+            type: enabled
+            budget_tokens: 16000
     - name: claude-opus-4-1@20250805
       max_input_tokens: 200000
       max_output_tokens: 8192
@@ -817,6 +871,31 @@
             thinking:
               type: enabled
               budget_tokens: 16000
+    - name: us.anthropic.claude-haiku-4-5-20251001-v1:0
+      max_input_tokens: 200000
+      max_output_tokens: 8192
+      require_max_tokens: true
+      input_price: 1
+      output_price: 5
+      supports_vision: true
+      supports_function_calling: true
+    - name: us.anthropic.claude-haiku-4-5-20251001-v1:0:thinking
+      real_name: us.anthropic.claude-haiku-4-5-20251001-v1:0
+      max_input_tokens: 200000
+      max_output_tokens: 24000
+      require_max_tokens: true
+      input_price: 1
+      output_price: 5
+      supports_vision: true
+      patch:
+        body:
+          inferenceConfig:
+            temperature: null
+            topP: null
+          additionalModelRequestFields:
+            thinking:
+              type: enabled
+              budget_tokens: 16000
     - name: us.anthropic.claude-opus-4-1-20250805-v1:0
       max_input_tokens: 200000
       max_output_tokens: 8192
@@ -1004,6 +1083,12 @@
       require_max_tokens: true
       input_price: 0
       output_price: 0
+    - name: '@cf/qwen/qwen3-30b-a3b-fp8'
+      max_input_tokens: 131072
+      max_output_tokens: 2048
+      require_max_tokens: true
+      input_price: 0
+      output_price: 0
     - name: '@cf/qwen/qwen2.5-coder-32b-instruct'
       max_input_tokens: 131072
       max_output_tokens: 2048
@@ -1030,8 +1115,8 @@
       max_batch_size: 100
 
 # Links:
-#  - https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Wm9cvy6rl
+#  - https://cloud.baidu.com/doc/qianfan/s/rmh4stp0j
-#  - https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Qm9cw2s7m
+#  - https://cloud.baidu.com/doc/qianfan/s/wmh4sv6ya
 - provider: ernie
   models:
     - name: ernie-4.5-turbo-128k
@@ -1043,8 +1128,12 @@
       input_price: 0.42
       output_price: 1.26
       supports_vision: true
-    - name: ernie-x1-turbo-32k
+    - name: ernie-5.0-thinking-preview
-      max_input_tokens: 32768
+      max_input_tokens: 131072
+      input_price: 1.4
+      output_price: 5.6
+    - name: ernie-x1.1-preview
+      max_input_tokens: 65536
       input_price: 0.14
       output_price: 0.56
     - name: bge-large-zh
@@ -1064,75 +1153,31 @@
       max_input_tokens: 1024
       input_price: 0.07
 
+
 # Links:
 #  - https://help.aliyun.com/zh/model-studio/getting-started/models
 #  - https://help.aliyun.com/zh/model-studio/developer-reference/use-qwen-by-calling-api
 - provider: qianwen
   models:
-    - name: qwen-max-latest
-      max_input_tokens: 32678
-      max_output_tokens: 8192
-      input_price: 1.6
-      output_price: 6.4
-      supports_function_calling: true
-    - name: qwen-plus-latest
-      max_input_tokens: 131072
-      max_output_tokens: 8192
-      input_price: 0.112
-      output_price: 0.28
-      supports_function_calling: true
-    - name: qwen-turbo-latest
-      max_input_tokens: 1000000
-      max_output_tokens: 8192
-      input_price: 0.042
-      output_price: 0.084
-      supports_function_calling: true
-    - name: qwen-long
-      max_input_tokens: 1000000
-      input_price: 0.07
-      output_price: 0.28
-    - name: qwen-omni-turbo-latest
-      max_input_tokens: 32768
-      max_output_tokens: 2048
-      supports_vision: true
-    - name: qwen-coder-plus-latest
-      max_input_tokens: 131072
-      max_output_tokens: 8192
-      input_price: 0.49
-      output_price: 0.98
-    - name: qwen-coder-turbo-latest
-      max_input_tokens: 131072
-      max_output_tokens: 8192
-      input_price: 0.28
-      output_price: 0.84
-    - name: qwen-vl-max-latest
-      max_input_tokens: 30720
-      max_output_tokens: 2048
-      input_price: 0.42
-      output_price: 1.26
-      supports_vision: true
-    - name: qwen-vl-plus-latest
-      max_input_tokens: 30000
-      max_output_tokens: 2048
-      input_price: 0.21
-      output_price: 0.63
-      supports_vision: true
     - name: qwen3-max
       max_input_tokens: 262144
-      input_price: 2.1
+      supports_function_calling: true
-      output_price: 8.4
+    - name: qwen-plus
+      max_input_tokens: 131072
+      supports_function_calling: true
+    - name: qwen-flash
+      max_input_tokens: 1000000
       supports_function_calling: true
     - name: qwen3-vl-plus
       max_input_tokens: 262144
-      input_price: 0.42
-      output_price: 4.2
       supports_vision: true
-    - name: qwen3-max-preview
+    - name: qwen3-vl-flash
       max_input_tokens: 262144
-      max_output_tokens: 32768
+      supports_vision: true
-      input_price: 1.4
+    - name: qwen-coder-plus
-      output_price: 5.6
+      max_input_tokens: 1000000
-      supports_function_calling: true
+    - name: qwen-coder-flash
+      max_input_tokens: 1000000
     - name: qwen3-next-80b-a3b-instruct
       max_input_tokens: 131072
       input_price: 0.14
@@ -1160,6 +1205,16 @@
       max_input_tokens: 131072
       input_price: 0.105
       output_price: 1.05
+    - name: qwen3-vl-32b-instruct
+      max_input_tokens: 131072
+      input_price: 0.28
+      output_price: 1.12
+      supports_vision: true
+    - name: qwen3-vl-8b-instruct
+      max_input_tokens: 131072
+      input_price: 0.07
+      output_price: 0.28
+      supports_vision: true
     - name: qwen3-coder-480b-a35b-instruct
       max_input_tokens: 262144
       input_price: 1.26
@@ -1168,32 +1223,10 @@
       max_input_tokens: 262144
       input_price: 0.315
       output_price: 1.26
-    - name: qwen2.5-72b-instruct
+    - name: deepseek-v3.2-exp
-      max_input_tokens: 129024
-      max_output_tokens: 8192
-      input_price: 0.56
-      output_price: 1.68
-      supports_function_calling: true
-    - name: qwen2.5-vl-72b-instruct
-      max_input_tokens: 129024
-      max_output_tokens: 8192
-      input_price: 2.24
-      output_price: 6.72
-      supports_vision: true
-    - name: qwen2.5-coder-32b-instruct
-      max_input_tokens: 129024
-      max_output_tokens: 8192
-      input_price: 0.49
-      output_price: 0.98
-      supports_function_calling: true
-    - name: deepseek-v3.1
       max_input_tokens: 131072
       input_price: 0.28
-      output_price: 1.12
+      output_price: 0.42
-    - name: deepseek-r1-0528
-      max_input_tokens: 65536
-      input_price: 0.28
-      output_price: 1.12
     - name: text-embedding-v4
       type: embedding
       input_price: 0.1
@@ -1247,10 +1280,10 @@
 #  - https://platform.moonshot.cn/docs/api/chat#%E5%85%AC%E5%BC%80%E7%9A%84%E6%9C%8D%E5%8A%A1%E5%9C%B0%E5%9D%80
 - provider: moonshot
   models:
-    - name: kimi-latest
+    - name: kimi-k2-turbo-preview
-      max_input_tokens: 131072
+      max_input_tokens: 262144
-      input_price: 1.4
+      input_price: 1.12
-      output_price: 4.2
+      output_price: 8.12
       supports_vision: true
       supports_function_calling: true
     - name: kimi-k2-0905-preview
@@ -1259,16 +1292,15 @@
       output_price: 2.24
       supports_vision: true
       supports_function_calling: true
-    - name: kimi-k2-turbo-preview
+    - name: kimi-k2-thinking-turbo
-      max_input_tokens: 131072
+      max_input_tokens: 262144
       input_price: 1.12
-      output_price: 4.48
+      output_price: 8.12
       supports_vision: true
-      supports_function_calling: true
+    - name: kimi-k2-thinking
-    - name: kimi-thinking-preview
+      max_input_tokens: 262144
-      max_input_tokens: 131072
+      input_price: 0.56
-      input_price: 28
+      output_price: 2.24
-      output_price: 28
       supports_vision: true
 
 # Links:
@@ -1293,7 +1325,7 @@
 #  - https://open.bigmodel.cn/dev/api#glm-4
 - provider: zhipuai
   models:
-    - name: glm-4.5
+    - name: glm-4.6
       max_input_tokens: 202752
       input_price: 0.28
       output_price: 1.12
@@ -1353,25 +1385,35 @@
       input_price: 0.112
 
 # Links:
-# - https://platform.minimaxi.com/document/pricing
+# - https://platform.minimaxi.com/docs/guides/pricing
 # - https://platform.minimaxi.com/document/ChatCompletion%20v2
 - provider: minimax
   models:
-    - name: minimax-text-01
+    - name: minimax-m2
-      max_input_tokens: 1000192
+      max_input_tokens: 204800
-      input_price: 0.14
+      input_price: 0.294
-      output_price: 1.12
+      output_price: 1.176
-      supports_vision: true
+      supports_function_calling: true
-    - name: minimax-m1
-      max_input_tokens: 131072
-      input_price: 0.112
-      output_price: 1.12
 
 # Links:
 #  - https://openrouter.ai/models
 #  - https://openrouter.ai/docs/api-reference/chat-completion
 - provider: openrouter
   models:
+    - name: openai/gpt-5.1
+      max_input_tokens: 400000
+      max_output_tokens: 128000
+      input_price: 1.25
+      output_price: 10
+      supports_vision: true
+      supports_function_calling: true
+    - name: openai/gpt-5.1-chat
+      max_input_tokens: 400000
+      max_output_tokens: 128000
+      input_price: 1.25
+      output_price: 10
+      supports_vision: true
+      supports_function_calling: true
     - name: openai/gpt-5
       max_input_tokens: 400000
       max_output_tokens: 128000
@@ -1400,13 +1442,6 @@
       output_price: 0.4
       supports_vision: true
       supports_function_calling: true
-    - name: openai/gpt-5-codex
-      max_input_tokens: 400000
-      max_output_tokens: 128000
-      input_price: 1.25
-      output_price: 10
-      supports_vision: true
-      supports_function_calling: true
     - name: openai/gpt-4.1
       max_input_tokens: 1047576
       max_output_tokens: 32768
@@ -1563,6 +1598,14 @@
       output_price: 15
       supports_vision: true
       supports_function_calling: true
+    - name: anthropic/claude-haiku-4.5
+      max_input_tokens: 200000
+      max_output_tokens: 8192
+      require_max_tokens: true
+      input_price: 1
+      output_price: 5
+      supports_vision: true
+      supports_function_calling: true
     - name: anthropic/claude-opus-4.1
       max_input_tokens: 200000
       max_output_tokens: 8192
@@ -1696,11 +1739,10 @@
       patch:
         body:
           include_reasoning: true
-    - name: qwen/qwen-max
+    - name: qwen/qwen3-max
-      max_input_tokens: 32768
+      max_input_tokens: 262144
-      max_output_tokens: 8192
+      input_price: 1.2
-      input_price: 1.6
+      output_price: 6
-      output_price: 6.4
       supports_function_calling: true
     - name: qwen/qwen-plus
       max_input_tokens: 131072
@@ -1708,22 +1750,6 @@
       input_price: 0.4
       output_price: 1.2
       supports_function_calling: true
-    - name: qwen/qwen-turbo
-      max_input_tokens: 1000000
-      max_output_tokens: 8192
-      input_price: 0.05
-      output_price: 0.2
-      supports_function_calling: true
-    - name: qwen/qwen-vl-plus
-      max_input_tokens: 7500
-      input_price: 0.21
-      output_price: 0.63
-      supports_vision: true
-    - name: qwen/qwen3-max
-      max_input_tokens: 262144
-      input_price: 1.2
-      output_price: 6
-      supports_function_calling: true
     - name: qwen/qwen3-next-80b-a3b-instruct
       max_input_tokens: 262144
       input_price: 0.1
@@ -1733,7 +1759,7 @@
       max_input_tokens: 262144
       input_price: 0.1
       output_price: 0.8
-    - name: qwen/qwen3-235b-a22b-2507
+    - name: qwen/qwen5-235b-a22b-2507 # Qwen3 235B A22B Instruct 2507
       max_input_tokens: 262144
       input_price: 0.12
       output_price: 0.59
@@ -1750,6 +1776,16 @@
       max_input_tokens: 262144
       input_price: 0.071
       output_price: 0.285
+    - name: qwen/qwen3-vl-32b-instruct
+      max_input_tokens: 262144
+      input_price: 0.35
+      output_price: 1.1
+      supports_vision: true
+    - name: qwen/qwen3-vl-8b-instruct
+      max_input_tokens: 262144
+      input_price: 0.08
+      output_price: 0.50
+      supports_vision: true
     - name: qwen/qwen3-coder-plus
       max_input_tokens: 128000
       input_price: 1
@@ -1760,30 +1796,26 @@
       input_price: 0.3
       output_price: 1.5
       supports_function_calling: true
+    - name: qwen/qwen3-coder  # Qwen3 Coder 480B A35B
+      max_input_tokens: 262144
+      input_price: 0.22
+      output_price: 0.95
+      supports_function_calling: true
     - name: qwen/qwen3-coder-30b-a3b-instruct
       max_input_tokens: 262144
       input_price: 0.052
       output_price: 0.207
       supports_function_calling: true
-    - name: qwen/qwen-2.5-72b-instruct
-      max_input_tokens: 131072
-      input_price: 0.35
-      output_price: 0.4
-      supports_function_calling: true
-    - name: qwen/qwen2.5-vl-72b-instruct
-      max_input_tokens: 32000
-      input_price: 0.7
-      output_price: 0.7
-      supports_vision: true
-    - name: qwen/qwen-2.5-coder-32b-instruct
-      max_input_tokens: 32768
-      input_price: 0.18
-      output_price: 0.18
     - name: moonshotai/kimi-k2-0905
       max_input_tokens: 262144
       input_price: 0.296
       output_price: 1.185
       supports_function_calling: true
+    - name: moonshotai/kimi-k2-thinking
+      max_input_tokens: 262144
+      input_price: 0.45
+      output_price: 2.35
+      supports_function_calling: true
     - name: moonshotai/kimi-dev-72b
       max_input_tokens: 131072
       input_price: 0.29
@@ -1804,6 +1836,11 @@
       input_price: 0.2
       output_price: 1.5
       supports_function_calling: true
+    - name: amazon/nova-premier-v1
+      max_input_tokens: 1000000
+      input_price: 2.5
+      output_price: 12.5
+      supports_vision: true
     - name: amazon/nova-pro-v1
       max_input_tokens: 300000
       max_output_tokens: 5120
@@ -1850,29 +1887,15 @@
       patch:
         body:
           include_reasoning: true
-    - name: minimax/minimax-01
+    - name: minimax/minimax-m2
-      max_input_tokens: 1000192
+      max_input_tokens: 196608
-      input_price: 0.2
+      input_price: 0.15
-      output_price: 1.1
+      output_price: 0.45
     - name: z-ai/glm-4.6
       max_input_tokens: 202752
       input_price: 0.5
       output_price: 1.75
       supports_function_calling: true
-    - name: z-ai/glm-4.5
-      max_input_tokens: 131072
-      input_price: 0.2
-      output_price: 0.2
-      supports_function_calling: true
-    - name: z-ai/glm-4.5-air
-      max_input_tokens: 131072
-      input_price: 0.2
-      output_price: 1.1
-    - name: z-ai/glm-4.5v
-      max_input_tokens: 65536
-      input_price: 0.5
-      output_price: 1.7
-      supports_vision: true
 
 # Links:
 #  - https://github.com/marketplace?type=models
@@ -2068,10 +2091,6 @@
       input_price: 0.08
       output_price: 0.3
       supports_vision: true
-    - name: meta-llama/Llama-3.3-70B-Instruct
-      max_input_tokens: 131072
-      input_price: 0.23
-      output_price: 0.40
     - name: Qwen/Qwen3-Next-80B-A3B-Instruct
       max_input_tokens: 262144
       input_price: 0.14
@@ -2100,27 +2119,15 @@
       input_price: 0.07
       output_price: 0.27
       supports_function_calling: true
-    - name: Qwen/Qwen3-235B-A22B
-      max_input_tokens: 40960
-      input_price: 0.15
-      output_price: 0.6
     - name: Qwen/Qwen3-30B-A3B
       max_input_tokens: 40960
       input_price: 0.1
       output_price: 0.3
-    - name: Qwen/Qwen3-32B
+    - name: Qwen/Qwen3-VL-8B-Instruct
-      max_input_tokens: 40960
+      max_input_tokens: 262144
-      input_price: 0.1
+      input_price: 0.18
-      output_price: 0.3
+      output_price: 0.69
-    - name: Qwen/Qwen2.5-72B-Instruct
+      supports_vision: true
-      max_input_tokens: 32768
-      input_price: 0.23
-      output_price: 0.40
-      supports_function_calling: true
-    - name: Qwen/Qwen2.5-Coder-32B-Instruct
-      max_input_tokens: 32768
-      input_price: 0.07
-      output_price: 0.16
     - name: deepseek-ai/DeepSeek-V3.2-Exp
       max_input_tokens: 163840
       input_price: 0.27
@@ -2145,35 +2152,21 @@
       max_input_tokens: 32768
       input_price: 0.06
       output_price: 0.12
-    - name: mistralai/Devstral-Small-2507
-      max_input_tokens: 131072
-      input_price: 0.07
-      output_price: 0.28
     - name: moonshotai/Kimi-K2-Instruct-0905
       max_input_tokens: 262144
       input_price: 0.5
       output_price: 2.0
       supports_function_calling: true
+    - name: moonshotai/Kimi-K2-Thinking
+      max_input_tokens: 262144
+      input_price: 0.55
+      output_price: 2.5
+      supports_function_calling: true
     - name: zai-org/GLM-4.6
       max_input_tokens: 202752
       input_price: 0.6
       output_price: 1.9
       supports_function_calling: true
-    - name: zai-org/GLM-4.5
-      max_input_tokens: 131072
-      input_price: 0.55
-      output_price: 2.0
-      supports_function_calling: true
-    - name: zai-org/GLM-4.5-Air
-      max_input_tokens: 131072
-      input_price: 0.2
-      output_price: 1.1
-      supports_function_calling: true
-    - name: zai-org/GLM-4.5V
-      max_input_tokens: 65536
-      input_price: 0.5
-      output_price: 1.7
-      supports_vision: true
     - name: BAAI/bge-large-en-v1.5
       type: embedding
       input_price: 0.01

src/config/mod.rs

@@ -24,7 +24,8 @@ use crate::utils::*;
 
 use crate::config::macros::Macro;
 use crate::mcp::{
-    MCP_INVOKE_META_FUNCTION_NAME_PREFIX, MCP_LIST_META_FUNCTION_NAME_PREFIX, McpRegistry,
+    MCP_DESCRIBE_META_FUNCTION_NAME_PREFIX, MCP_INVOKE_META_FUNCTION_NAME_PREFIX,
+    MCP_SEARCH_META_FUNCTION_NAME_PREFIX, McpRegistry,
 };
 use crate::vault::{GlobalVault, Vault, create_vault_password_file, interpolate_secrets};
 use anyhow::{Context, Result, anyhow, bail};
@@ -799,7 +800,7 @@ impl Config {
                             || s == "all"
                     }) {
                         bail!(
-                            "Some of the specified MCP servers in 'enabled_mcp_servers' are configured. Please check your MCP server configuration."
+                            "Some of the specified MCP servers in 'enabled_mcp_servers' are not fully configured. Please check your MCP server configuration."
                         );
                     }
                 }
@@ -1972,7 +1973,8 @@ impl Config {
                     .iter()
                     .filter(|v| {
                         !v.name.starts_with(MCP_INVOKE_META_FUNCTION_NAME_PREFIX)
-                            && !v.name.starts_with(MCP_LIST_META_FUNCTION_NAME_PREFIX)
+                            && !v.name.starts_with(MCP_SEARCH_META_FUNCTION_NAME_PREFIX)
+                            && !v.name.starts_with(MCP_DESCRIBE_META_FUNCTION_NAME_PREFIX)
                     })
                     .map(|v| v.name.to_string())
                     .collect();
@@ -2015,7 +2017,8 @@ impl Config {
                     .into_iter()
                     .filter(|v| {
                         !v.name.starts_with(MCP_INVOKE_META_FUNCTION_NAME_PREFIX)
-                            && !v.name.starts_with(MCP_LIST_META_FUNCTION_NAME_PREFIX)
+                            && !v.name.starts_with(MCP_SEARCH_META_FUNCTION_NAME_PREFIX)
+                            && !v.name.starts_with(MCP_DESCRIBE_META_FUNCTION_NAME_PREFIX)
                     })
                     .collect();
                 let tool_names: HashSet<String> = agent_functions
@@ -2051,7 +2054,8 @@ impl Config {
                     .iter()
                     .filter(|v| {
                         v.name.starts_with(MCP_INVOKE_META_FUNCTION_NAME_PREFIX)
-                            || v.name.starts_with(MCP_LIST_META_FUNCTION_NAME_PREFIX)
+                            || v.name.starts_with(MCP_SEARCH_META_FUNCTION_NAME_PREFIX)
+                            || v.name.starts_with(MCP_DESCRIBE_META_FUNCTION_NAME_PREFIX)
                     })
                     .map(|v| v.name.to_string())
                     .collect();
@@ -2062,8 +2066,10 @@ impl Config {
                         let item = item.trim();
                         let item_invoke_name =
                             format!("{}_{item}", MCP_INVOKE_META_FUNCTION_NAME_PREFIX);
-                        let item_list_name =
+                        let item_search_name =
-                            format!("{}_{item}", MCP_LIST_META_FUNCTION_NAME_PREFIX);
+                            format!("{}_{item}", MCP_SEARCH_META_FUNCTION_NAME_PREFIX);
+                        let item_describe_name =
+                            format!("{}_{item}", MCP_DESCRIBE_META_FUNCTION_NAME_PREFIX);
                         if let Some(values) = self.mapping_mcp_servers.get(item) {
                             server_names.extend(
                                 values
@@ -2077,7 +2083,12 @@ impl Config {
                                             ),
                                             format!(
                                                 "{}_{}",
-                                                MCP_LIST_META_FUNCTION_NAME_PREFIX,
+                                                MCP_SEARCH_META_FUNCTION_NAME_PREFIX,
+                                                v.to_string()
+                                            ),
+                                            format!(
+                                                "{}_{}",
+                                                MCP_DESCRIBE_META_FUNCTION_NAME_PREFIX,
                                                 v.to_string()
                                             ),
                                         ]
@@ -2086,7 +2097,8 @@ impl Config {
                             )
                         } else if mcp_declaration_names.contains(&item_invoke_name) {
                             server_names.insert(item_invoke_name);
-                            server_names.insert(item_list_name);
+                            server_names.insert(item_search_name);
+                            server_names.insert(item_describe_name);
                         }
                     }
                 }
@@ -2112,7 +2124,8 @@ impl Config {
                     .into_iter()
                     .filter(|v| {
                         v.name.starts_with(MCP_INVOKE_META_FUNCTION_NAME_PREFIX)
-                            || v.name.starts_with(MCP_LIST_META_FUNCTION_NAME_PREFIX)
+                            || v.name.starts_with(MCP_SEARCH_META_FUNCTION_NAME_PREFIX)
+                            || v.name.starts_with(MCP_DESCRIBE_META_FUNCTION_NAME_PREFIX)
                     })
                     .collect();
                 let tool_names: HashSet<String> = agent_functions

src/function/mod.rs

@@ -4,7 +4,10 @@ use crate::{
 };
 
 use crate::config::ensure_parent_exists;
-use crate::mcp::{MCP_INVOKE_META_FUNCTION_NAME_PREFIX, MCP_LIST_META_FUNCTION_NAME_PREFIX};
+use crate::mcp::{
+    MCP_DESCRIBE_META_FUNCTION_NAME_PREFIX, MCP_INVOKE_META_FUNCTION_NAME_PREFIX,
+    MCP_SEARCH_META_FUNCTION_NAME_PREFIX,
+};
 use crate::parsers::{bash, python};
 use anyhow::{Context, Result, anyhow, bail};
 use indexmap::IndexMap;
@@ -247,19 +250,13 @@ impl Functions {
     pub fn clear_mcp_meta_functions(&mut self) {
         self.declarations.retain(|d| {
             !d.name.starts_with(MCP_INVOKE_META_FUNCTION_NAME_PREFIX)
-                && !d.name.starts_with(MCP_LIST_META_FUNCTION_NAME_PREFIX)
+                && !d.name.starts_with(MCP_SEARCH_META_FUNCTION_NAME_PREFIX)
+                && !d.name.starts_with(MCP_DESCRIBE_META_FUNCTION_NAME_PREFIX)
         });
     }
 
     pub fn append_mcp_meta_functions(&mut self, mcp_servers: Vec<String>) {
         let mut invoke_function_properties = IndexMap::new();
-        invoke_function_properties.insert(
-            "server".to_string(),
-            JsonSchema {
-                type_value: Some("string".to_string()),
-                ..Default::default()
-            },
-        );
         invoke_function_properties.insert(
             "tool".to_string(),
             JsonSchema {
@@ -275,32 +272,86 @@ impl Functions {
             },
         );
 
+        let mut search_function_properties = IndexMap::new();
+        search_function_properties.insert(
+            "query".to_string(),
+            JsonSchema {
+                type_value: Some("string".to_string()),
+                description: Some("Generalized explanation of what you want to do".into()),
+                ..Default::default()
+            },
+        );
+        search_function_properties.insert(
+            "top_k".to_string(),
+            JsonSchema {
+                type_value: Some("integer".to_string()),
+                description: Some("How many results to return, between 1 and 20".into()),
+                default: Some(Value::from(8usize)),
+                ..Default::default()
+            },
+        );
+
+        let mut describe_function_properties = IndexMap::new();
+        describe_function_properties.insert(
+            "tool".to_string(),
+            JsonSchema {
+                type_value: Some("string".to_string()),
+                description: Some("The name of the tool; e.g., search_issues".into()),
+                ..Default::default()
+            },
+        );
+
         for server in mcp_servers {
+            let search_function_name = format!("{}_{server}", MCP_SEARCH_META_FUNCTION_NAME_PREFIX);
+            let describe_function_name =
+                format!("{}_{server}", MCP_DESCRIBE_META_FUNCTION_NAME_PREFIX);
             let invoke_function_name = format!("{}_{server}", MCP_INVOKE_META_FUNCTION_NAME_PREFIX);
             let invoke_function_declaration = FunctionDeclaration {
                 name: invoke_function_name.clone(),
                 description: formatdoc!(
                     r#"
-										Invoke the specified tool on the {server} MCP server. Always call {invoke_function_name} first to find the
+										Invoke the specified tool on the {server} MCP server. Always call {describe_function_name} first to
-										correct names of tools before calling '{invoke_function_name}'.
+										find the correct invocation schema for the given tool.
 										"#
                 ),
                 parameters: JsonSchema {
                     type_value: Some("object".to_string()),
                     properties: Some(invoke_function_properties.clone()),
-                    required: Some(vec!["server".to_string(), "tool".to_string()]),
+                    required: Some(vec!["tool".to_string()]),
                     ..Default::default()
                 },
                 agent: false,
             };
-            let list_functions_declaration = FunctionDeclaration {
+            let search_functions_declaration = FunctionDeclaration {
-                name: format!("{}_{}", MCP_LIST_META_FUNCTION_NAME_PREFIX, server),
+                name: search_function_name.clone(),
-                description: format!("List all the available tools for the {server} MCP server"),
+                description: formatdoc!(
-                parameters: JsonSchema::default(),
+                    r#"
+                    Find candidate tools by keywords for the {server} MCP server. Returns small suggestions; fetch
+                    schemas with {describe_function_name}.
+                    "#
+                ),
+                parameters: JsonSchema {
+                    type_value: Some("object".to_string()),
+                    properties: Some(search_function_properties.clone()),
+                    required: Some(vec!["query".to_string()]),
+                    ..Default::default()
+                },
+                agent: false,
+            };
+            let describe_functions_declaration = FunctionDeclaration {
+                name: describe_function_name.clone(),
+                description: "Get the full JSON schema for exactly one MCP tool.".to_string(),
+                parameters: JsonSchema {
+                    type_value: Some("object".to_string()),
+                    properties: Some(describe_function_properties.clone()),
+                    required: Some(vec!["tool".to_string()]),
+                    ..Default::default()
+                },
                 agent: false,
             };
             self.declarations.push(invoke_function_declaration);
-            self.declarations.push(list_functions_declaration);
+            self.declarations.push(search_functions_declaration);
+            self.declarations.push(describe_functions_declaration);
         }
     }
 
@@ -771,7 +822,37 @@ impl ToolCall {
         }
 
         let output = match cmd_name.as_str() {
-            _ if cmd_name.starts_with(MCP_LIST_META_FUNCTION_NAME_PREFIX) => {
+            _ if cmd_name.starts_with(MCP_SEARCH_META_FUNCTION_NAME_PREFIX) => {
+                Self::search_mcp_tools(config, &cmd_name, &json_data)?
+            }
+            _ if cmd_name.starts_with(MCP_DESCRIBE_META_FUNCTION_NAME_PREFIX) => {
+                Self::describe_mcp_tool(config, &cmd_name, json_data).await?
+            }
+            _ if cmd_name.starts_with(MCP_INVOKE_META_FUNCTION_NAME_PREFIX) => {
+                Self::invoke_mcp_tool(config, &cmd_name, &json_data).await?
+            }
+            _ => match run_llm_function(cmd_name, cmd_args, envs, agent_name)? {
+                Some(contents) => serde_json::from_str(&contents)
+                    .ok()
+                    .unwrap_or_else(|| json!({"output": contents})),
+                None => Value::Null,
+            },
+        };
+
+        Ok(output)
+    }
+
+    async fn describe_mcp_tool(
+        config: &GlobalConfig,
+        cmd_name: &str,
+        json_data: Value,
+    ) -> Result<Value> {
+        let server_id = cmd_name.replace(&format!("{MCP_DESCRIBE_META_FUNCTION_NAME_PREFIX}_"), "");
+        let tool = json_data
+            .get("tool")
+            .ok_or_else(|| anyhow!("Missing 'tool' in arguments"))?
+            .as_str()
+            .ok_or_else(|| anyhow!("Invalid 'tool' in arguments"))?;
         let registry_arc = {
             let cfg = config.read();
             cfg.mcp_registry
@@ -779,14 +860,44 @@ impl ToolCall {
                 .with_context(|| "MCP is not configured")?
         };
 
-                registry_arc.catalog().await?
+        let result = registry_arc.describe(&server_id, tool).await?;
+        Ok(serde_json::to_value(result)?)
     }
-            _ if cmd_name.starts_with(MCP_INVOKE_META_FUNCTION_NAME_PREFIX) => {
+
-                let server = json_data
+    fn search_mcp_tools(config: &GlobalConfig, cmd_name: &str, json_data: &Value) -> Result<Value> {
-                    .get("server")
+        let server = cmd_name.replace(&format!("{MCP_SEARCH_META_FUNCTION_NAME_PREFIX}_"), "");
-                    .ok_or_else(|| anyhow!("Missing 'server' in arguments"))?
+        let query = json_data
+            .get("query")
+            .ok_or_else(|| anyhow!("Missing 'query' in arguments"))?
             .as_str()
-                    .ok_or_else(|| anyhow!("Invalid 'server' in arguments"))?;
+            .ok_or_else(|| anyhow!("Invalid 'query' in arguments"))?;
+        let top_k = json_data
+            .get("top_k")
+            .cloned()
+            .unwrap_or_else(|| Value::from(8u64))
+            .as_u64()
+            .ok_or_else(|| anyhow!("Invalid 'top_k' in arguments"))? as usize;
+        let registry_arc = {
+            let cfg = config.read();
+            cfg.mcp_registry
+                .clone()
+                .with_context(|| "MCP is not configured")?
+        };
+
+        let catalog_items = registry_arc
+            .search_tools_server(&server, query, top_k)
+            .into_iter()
+            .map(|it| serde_json::to_value(&it).unwrap_or_default())
+            .collect();
+        Ok(Value::Array(catalog_items))
+    }
+
+    async fn invoke_mcp_tool(
+        config: &GlobalConfig,
+        cmd_name: &str,
+        json_data: &Value,
+    ) -> Result<Value> {
+        let server = cmd_name.replace(&format!("{MCP_INVOKE_META_FUNCTION_NAME_PREFIX}_"), "");
         let tool = json_data
             .get("tool")
             .ok_or_else(|| anyhow!("Missing 'tool' in arguments"))?
@@ -802,18 +913,9 @@ impl ToolCall {
                 .clone()
                 .with_context(|| "MCP is not configured")?
         };
-                let result = registry_arc.invoke(server, tool, arguments).await?;
-                serde_json::to_value(result)?
-            }
-            _ => match run_llm_function(cmd_name, cmd_args, envs, agent_name)? {
-                Some(contents) => serde_json::from_str(&contents)
-                    .ok()
-                    .unwrap_or_else(|| json!({"output": contents})),
-                None => Value::Null,
-            },
-        };
 
-        Ok(output)
+        let result = registry_arc.invoke(&server, tool, arguments).await?;
+        Ok(serde_json::to_value(result)?)
     }
 
     fn extract_call_config_from_agent(

src/mcp/mod.rs

@@ -2,6 +2,7 @@ use crate::config::Config;
 use crate::utils::{AbortSignal, abortable_run_with_spinner};
 use crate::vault::interpolate_secrets;
 use anyhow::{Context, Result, anyhow};
+use bm25::{Document, Language, SearchEngine, SearchEngineBuilder};
 use futures_util::future::BoxFuture;
 use futures_util::{StreamExt, TryStreamExt, stream};
 use indoc::formatdoc;
@@ -9,7 +10,7 @@ use rmcp::model::{CallToolRequestParam, CallToolResult};
 use rmcp::service::RunningService;
 use rmcp::transport::TokioChildProcess;
 use rmcp::{RoleClient, ServiceExt};
-use serde::Deserialize;
+use serde::{Deserialize, Serialize};
 use serde_json::{Value, json};
 use std::borrow::Cow;
 use std::collections::{HashMap, HashSet};
@@ -20,10 +21,46 @@ use std::sync::Arc;
 use tokio::process::Command;
 
 pub const MCP_INVOKE_META_FUNCTION_NAME_PREFIX: &str = "mcp_invoke";
-pub const MCP_LIST_META_FUNCTION_NAME_PREFIX: &str = "mcp_list";
+pub const MCP_SEARCH_META_FUNCTION_NAME_PREFIX: &str = "mcp_search";
+pub const MCP_DESCRIBE_META_FUNCTION_NAME_PREFIX: &str = "mcp_describe";
 
 type ConnectedServer = RunningService<RoleClient, ()>;
 
+#[derive(Clone, Debug, Default, Serialize)]
+pub struct CatalogItem {
+    pub name: String,
+    pub server: String,
+    pub description: String,
+}
+
+#[derive(Debug)]
+struct ServerCatalog {
+    engine: SearchEngine<String>,
+    items: HashMap<String, CatalogItem>,
+}
+
+impl ServerCatalog {
+    pub fn build_bm25(items: &HashMap<String, CatalogItem>) -> SearchEngine<String> {
+        let docs = items.values().map(|it| {
+            let contents = format!("{}\n{}\nserver:{}", it.name, it.description, it.server);
+            Document {
+                id: it.name.clone(),
+                contents,
+            }
+        });
+        SearchEngineBuilder::<String>::with_documents(Language::English, docs).build()
+    }
+}
+
+impl Clone for ServerCatalog {
+    fn clone(&self) -> Self {
+        Self {
+            engine: Self::build_bm25(&self.items),
+            items: self.items.clone(),
+        }
+    }
+}
+
 #[derive(Debug, Clone, Deserialize)]
 struct McpServersConfig {
     #[serde(rename = "mcpServers")]
@@ -50,7 +87,8 @@ enum JsonField {
 pub struct McpRegistry {
     log_path: Option<PathBuf>,
     config: Option<McpServersConfig>,
-    servers: HashMap<String, Arc<RunningService<RoleClient, ()>>>,
+    servers: HashMap<String, Arc<ConnectedServer>>,
+    catalogs: HashMap<String, ServerCatalog>,
 }
 
 impl McpRegistry {
@@ -173,7 +211,7 @@ impl McpRegistry {
                     .collect()
             };
 
-            let results: Vec<(String, Arc<_>)> = stream::iter(
+            let results: Vec<(String, Arc<_>, ServerCatalog)> = stream::iter(
                 server_ids
                     .into_iter()
                     .map(|id| async { self.start_server(id).await }),
@@ -182,13 +220,24 @@ impl McpRegistry {
             .try_collect()
             .await?;
 
-            self.servers = results.into_iter().collect();
+            self.servers = results
+                .clone()
+                .into_iter()
+                .map(|(id, server, _)| (id, server))
+                .collect();
+            self.catalogs = results
+                .into_iter()
+                .map(|(id, _, catalog)| (id, catalog))
+                .collect();
         }
 
         Ok(())
     }
 
-    async fn start_server(&self, id: String) -> Result<(String, Arc<ConnectedServer>)> {
+    async fn start_server(
+        &self,
+        id: String,
+    ) -> Result<(String, Arc<ConnectedServer>, ServerCatalog)> {
         let server = self
             .config
             .as_ref()
@@ -231,14 +280,33 @@ impl McpRegistry {
                 .await
                 .with_context(|| format!("Failed to start MCP server: {}", &server.command))?,
         );
-        debug!(
+        let tools = service.list_tools(None).await?;
-            "Available tools for MCP server {id}: {:?}",
+        debug!("Available tools for MCP server {id}: {tools:?}");
-            service.list_tools(None).await?
+
-        );
+        let mut items_vec = Vec::new();
+        for t in tools.tools {
+            let name = t.name.to_string();
+            let description = t.description.unwrap_or_default().to_string();
+            items_vec.push(CatalogItem {
+                name,
+                server: id.clone(),
+                description,
+            });
+        }
+
+        let mut items_map = HashMap::new();
+        items_vec.into_iter().for_each(|it| {
+            items_map.insert(it.name.clone(), it);
+        });
+
+        let catalog = ServerCatalog {
+            engine: ServerCatalog::build_bm25(&items_map),
+            items: items_map,
+        };
 
         info!("Started MCP server: {id}");
 
-        Ok((id.to_string(), service))
+        Ok((id.to_string(), service, catalog))
     }
 
     pub async fn stop_all_servers(mut self) -> Result<Self> {
@@ -268,26 +336,48 @@ impl McpRegistry {
         }
     }
 
-    pub fn catalog(&self) -> BoxFuture<'static, Result<Value>> {
+    pub fn search_tools_server(&self, server: &str, query: &str, top_k: usize) -> Vec<CatalogItem> {
-        let servers: Vec<(String, Arc<ConnectedServer>)> = self
+        let Some(catalog) = self.catalogs.get(server) else {
+            return vec![];
+        };
+        let engine = &catalog.engine;
+        let raw = engine.search(query, top_k.min(20));
+
+        raw.into_iter()
+            .filter_map(|r| catalog.items.get(&r.document.id))
+            .take(top_k)
+            .cloned()
+            .collect()
+    }
+
+    pub async fn describe(&self, server_id: &str, tool: &str) -> Result<Value> {
+        let server = self
             .servers
             .iter()
-            .map(|(id, s)| (id.clone(), s.clone()))
+            .filter(|(id, _)| &server_id == id)
-            .collect();
+            .map(|(_, s)| s.clone())
+            .next()
+            .ok_or(anyhow!("{server_id} MCP server not found in config"))?;
 
-        Box::pin(async move {
+        let tool_schema = server
-            let mut out = Vec::with_capacity(servers.len());
+            .list_tools(None)
-            for (id, server) in servers {
+            .await?
-                let tools = server.list_tools(None).await?;
+            .tools
-                let resources = server.list_resources(None).await.unwrap_or_default();
+            .into_iter()
-                out.push(json!({
+            .find(|it| it.name == tool)
-                  "server": id,
+            .ok_or(anyhow!(
-                  "tools": tools,
+                "{tool} not found in {server_id} MCP server catalog"
-                  "resources": resources,
+            ))?
-                }));
+            .input_schema;
+        Ok(json!({
+            "type": "object",
+            "properties": {
+                "tool": {
+                    "type": "string",
+                },
+                "arguments": tool_schema
             }
-            Ok(Value::Array(out))
+        }))
-        })
     }
 
     pub fn invoke(