RAG MCP Server
by tungetti
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Port number for the server (default: not specified) | |
| TOP_K | No | Number of results to return (default: 7) | |
| VERBOSE | No | Enable verbose logging (default: false) | |
| CHUNK_SIZE | No | Maximum chunk size in characters (default: 500) | |
| CHUNK_OVERLAP | No | Chunk overlap size in characters (default: 200) | |
| KNOWLEDGE_BASE | No | Path to the document directory (default: none, must be provided via tool call or this variable) | |
| EMBEDDING_MODEL | No | Model name for embeddings (default: ibm-granite/granite-embedding-278m-multilingual) |
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
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/tungetti/rag-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server