rag-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RAG_MCP_DB_PATH | Yes | Path to the ChromaDB persistent directory | |
| RAG_MCP_EMBEDDER | No | Embedder model to use: 'miniLM' (default) or 'bge' | miniLM |
| RAG_MCP_COLLECTION | Yes | Name of the ChromaDB collection | |
| RAG_MCP_CORPUS_ROOT | Yes | Root directory of the corpus (auth scope) |
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
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_knowledgeA | Retrieve the most relevant passages from the configured knowledge corpus for a natural-language query. Returns the passage text plus a CITATION (source file + heading + chunk index) for each hit so answers are traceable. Auth-scoped to the corpus root and fail-soft: a down/empty store returns a structured error, never an exception. Use when asked to look something up in the knowledge base / docs. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
The single tool has a clear, distinct purpose (retrieving relevant passages). With no other tools to differentiate, there is no possibility of ambiguous selection.
The tool name 'search_knowledge' follows a clear verb_noun convention, which would be consistent even if more tools were added. As a single tool, it sets a predictable pattern.
With only one tool, the server feels too thin for the 'rag' domain, which typically requires additional operations like listing sources or ingesting content. The single tool is not trivial but is insufficient for a well-scoped RAG server.
The tool surface covers only search/retrieval. There are no tools for managing the knowledge corpus (e.g., list sources, add/update/delete documents), leaving significant gaps that would require external intervention for many workflows.