rag-mcp
by Ma-fee
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HTTP_HOST | No | SSE mode listen address | 127.0.0.1 |
| HTTP_PORT | No | SSE mode listen port | 8787 |
| CHUNK_SIZE | No | Chunk size in characters | 800 |
| CHUNK_OVERLAP | No | Chunk overlap in characters | 120 |
| DEFAULT_TOP_K | No | Default number of results | 5 |
| KEYWORD_TOP_K | No | Keyword search candidates | 8 |
| MCP_TRANSPORT | No | Transport mode: stdio or sse | stdio |
| EMBEDDING_MODEL | No | Embedding model | Qwen/Qwen3-Embedding-0.6B |
| RAG_MCP_DATA_DIR | No | Index data directory | .rag_mcp_data |
| EMBEDDING_API_KEY | Yes | Required for vector search | |
| EMBEDDING_BASE_URL | No | Embedding service URL | https://api.siliconflow.cn/v1 |
| EMBEDDING_DIMENSION | No | Vector dimension (optional, auto-detect) | |
| EMBEDDING_TIMEOUT_SECONDS | No | Request timeout seconds | 30 |
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 | |
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Ma-fee/RAG_MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server