rag-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RAG_MCP_HOST | No | HTTP host to bind when using streamable-http or sse transport (e.g. 0.0.0.0) | |
| RAG_MCP_PORT | No | HTTP port to bind when using streamable-http or sse transport | |
| RAG_MCP_KB_PATH | No | Override the knowledge base path set in config.yaml (takes precedence) | |
| RAG_MCP_TRANSPORT | No | MCP transport to use: stdio (default), streamable-http, or sse | |
| RAG_MCP_AUTH_TOKEN | No | Bearer token for HTTP authentication; setting this variable automatically enables auth | |
| RAG_MCP_RATE_LIMIT_RPS | No | Token bucket rate limit in requests per second (0 = disabled) | |
| RAG_MCP_RATE_LIMIT_BURST | No | Token bucket burst capacity (defaults to ceil(rps) if <= 0) | |
| RAG_MCP_EMBEDDING_OFFLINE | No | Embedding offline mode: true to only use local model cache, false to allow downloading the model | |
| RAG_MCP_SANITIZE_RETRIEVED | No | Whether to sanitize retrieved content for prompt injection (default true) |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues