Schema | mcp-ragchat

mcp-ragchat

Describes the environment variables required to run the server.

Name	Required	Description
`LLM_MODEL`	No	Override the default LLM model.
`AWS_REGION`	No	AWS region for Bedrock embeddings (amazon.titan-embed-text-v2:0). Requires IAM permissions.
`GEMINI_API_KEY`	No	API key for Google Gemini. Used for both LLM (gemini-2.0-flash) and embeddings (text-embedding-004) by default.
`OPENAI_API_KEY`	No	API key for OpenAI. Used for both LLM (gpt-4o-mini) and embeddings (text-embedding-3-small) by default.
`EMBEDDING_MODEL`	No	Override the default embedding model.
`ANTHROPIC_API_KEY`	No	API key for Anthropic. Used for LLM (claude-sonnet-4-5-20250929) by default.

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.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{ "listChanged": true }

Functions exposed to the LLM to take actions

Name	Description
ragchat_setupA	Initialize a domain with a knowledge base from markdown content. Each ## section becomes a searchable document with vector embeddings. This is the first step — run this before testing or serving.
ragchat_testA	Send a test message to a domain's chat. Uses RAG search + LLM to generate a response, same as production. Good for verifying the knowledge base works.
ragchat_serveA	Start a local HTTP chat server for a domain. The server runs on localhost and handles POST /chat requests. Use ragchat_widget to get the embed code that connects to this server.
ragchat_widgetA	Generate an embeddable chat widget. Returns a tag that creates a floating chat bubble on any webpage. Connects to the chat server started with ragchat_serve.
ragchat_statusA	List all configured domains with document counts and config status. Shows what's been set up and what's ready to serve.

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/gogabrielordonez/mcp-ragchat'

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