Code Index MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| set_project_pathC | Set the base project path for indexing. |
| search_code_advancedA | |
| find_filesA | |
| get_file_summaryA | |
| refresh_indexA | |
| get_settings_infoB | Get information about the project settings. |
| create_temp_directoryA | Create the temporary directory used for storing index data. |
| check_temp_directoryA | Check the temporary directory used for storing index data. |
| clear_settingsB | Clear all settings and cached data. |
| refresh_search_toolsA | Manually re-detect the available command-line search tools on the system. This is useful if you have installed a new tool (like ripgrep) after starting the server. |
| get_file_watcher_statusA | Get file watcher service status and statistics. |
| configure_file_watcherC | Configure file watcher service settings. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| analyze_code | Prompt for analyzing code in the project. |
| code_search | Prompt for searching code in the project. |
| set_project | Prompt for setting the project path. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| config://code-indexer | |
| structure://project | |
| settings://stats |
TDQS
Scored across 12 tools
Each tool has a clearly distinct purpose: checking vs creating temp directory, configuring vs getting watcher status, clearing vs getting settings, finding files vs searching code vs getting file summary, refreshing index vs refreshing search tools. No overlap or ambiguity.
All tool names follow a consistent verb_noun pattern with lowercase and underscores, e.g., check_temp_directory, get_file_summary, set_project_path. The verbs are diverse but each clearly indicates the action.
With 12 tools covering directory management, settings, file watching, file finding, code search, and index refresh, the count is well-scoped for the server's purpose. No tool feels redundant or missing.
The tool set covers key operations: setting project path, finding files, searching code, getting file summaries, refreshing index, and managing settings/watcher. Minor gaps exist, such as no explicit tool to list indexed files or get index status, but the core workflows are supported.