Agentic RAG MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RAG_MODEL | No | Model name for Claude (default: claude-opus-4-8) | |
| RAG_TOP_K | No | Number of top chunks to retrieve (default: 5) | |
| DATABASE_URL | Yes | PostgreSQL connection string with pgvector | |
| VOYAGE_API_KEY | Yes | Voyage API key for embeddings | |
| RAG_EMBED_MODEL | No | Embedding model name (default: voyage-3.5) | |
| ANTHROPIC_API_KEY | Yes | Anthropic API key for Claude | |
| FIRECRAWL_API_KEY | No | Optional Firecrawl API key for web research | |
| RAG_MAX_REVISIONS | No | Maximum number of revision cycles (default: 3) |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| 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
| Name | Description |
|---|---|
| ingestA | Add a web page to the knowledge base: scrape the URL, chunk and embed its text, and
store it so future |
| askA | Answer a QUESTION with a written, source-cited answer (the full multi-agent RAG
pipeline: plan → retrieve → synthesize → self-critique). Use this when the user wants an
ANSWER. For raw matching documents instead of a written answer, use |
| searchA | Retrieve the raw top-k source chunks matching a QUERY, with similarity scores and no
synthesized answer. Use this when you want the underlying documents themselves. To get a
written, cited answer instead, use |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool has a distinct purpose: 'ask' provides synthesized answers, 'search' returns raw chunks, and 'ingest' adds content. There is no overlap or ambiguity between them.
All tool names are single-word verbs in lowercase, following a consistent and predictable pattern. No mixing of conventions.
Three tools is ideal for this RAG server: one for ingestion, one for answering, and one for raw retrieval. The scope is well-defined without unnecessary tools.
The tool set covers the core RAG workflow (ingest, ask, search). A potential minor gap is the lack of a delete or update tool, but for the stated purpose it is highly complete.