Schema | CRAG-MCP

CRAG-MCP

Describes the environment variables required to run the server.

Name	Required	Description	Default
`CRAG_SMALL_LLM`	No	The small LLM model to use for semantic analysis (e.g., gemma4:31b-cloud)
`CRAG_WORKSPACE`	No	The workspace path for the server (default: current directory)

Features and capabilities supported by this server

Capability	Details
`tools`	{ "listChanged": true }
`logging`	{}
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`extensions`	{ "io.modelcontextprotocol/ui": {} }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
configureC	Configure workspace and LLM.
preprocess_configA	Load preprocessing config for conditional compilation. Call this when analyzing C/C++ projects with #ifdef blocks, Linux kernel with Kconfig, or Makefile-based builds. Supports: Linux .config files C header files with #define Makefiles with CFLAGS -D JSON files Manual define overrides
query_graphA	Search code graph. Automatically indexes relevant files. If preprocess_config() was called on the workspace, filters by active defines. Otherwise returns all functions (no filtering). Parses source files into the graph with AST (no LLM). Use summarize_function() on individual results for deep analysis.
read_function_bodyB	Read the full source code of a function.
summarize_functionA	Deep-analyze a single function with LLM (summary + call extraction). Call this after query_graph() to enrich specific functions. Results (summary, keywords, call edges) are stored in the graph and become available to get_callers(), get_callees(), get_call_path().
get_callersC	Find functions that call the given function.
get_calleesB	Find functions called by the given function.
get_call_pathA	Find call path between two functions using BFS. Requires call edges in the graph (populated by summarize_function()).
graph_statsC	Get graph statistics for a workspace.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/bluemot/crag-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server