Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
RAG_MODELNoModel name for Claude (default: claude-opus-4-8)
RAG_TOP_KNoNumber of top chunks to retrieve (default: 5)
DATABASE_URLYesPostgreSQL connection string with pgvector
VOYAGE_API_KEYYesVoyage API key for embeddings
RAG_EMBED_MODELNoEmbedding model name (default: voyage-3.5)
ANTHROPIC_API_KEYYesAnthropic API key for Claude
FIRECRAWL_API_KEYNoOptional Firecrawl API key for web research
RAG_MAX_REVISIONSNoMaximum number of revision cycles (default: 3)

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": true
}
logging
{}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
extensions
{
  "io.modelcontextprotocol/ui": {}
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
ingestA

Scrape a URL, chunk + embed it, and add it to the knowledge base.

askA

Answer a question with the multi-agent RAG pipeline; returns answer + citations.

searchA

Return the top-k most relevant stored chunks for a query (retrieval only).

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

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/enached134-ctrl/agentic-rag-mcp'

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