Skip to main content
Glama
n1khll

kb-rag-mcp

by n1khll
OverviewSchemaRelated ServersScoreDiscussions
Python
Remote

kb-rag-mcp

Standalone MCP server exposing agentic-RAG tools over a pgvector-backed knowledge base. Designed for public internet deployment (Render) with bearer-token auth; embeddings via Azure OpenAI; LLM/agent side lives in Azure AI Foundry (or any MCP-capable client).

Tools

Tool

Purpose

kb_search

Hybrid retrieval (vector + full-text, RRF-fused, MMR-diversified). Returns chunks + citations + confidence.

kb_get_article

Full article body by kb_number — for drilling into a promising hit.

kb_list_categories

Categories + article counts — for scoping a refined search.

kb_health

Chunk/article counts + last ingest time — distinguishes "empty KB" from "no match".

microsoft_learn

Official Microsoft docs (Microsoft Learn) — external fallback for Microsoft-product questions. One tool, three modes: search (default), code_sample (commands/scripts, optional language), fetch (full page by url).

The agentic loop lives in the client agent: search the internal KB → check low_confidence → refine / scope by category / fetch full article → answer with citations. For Microsoft-product questions the KB doesn't cover, it falls back to Microsoft Learn (clearly labeled as external).

Microsoft Learn tools proxy the official public MS Learn MCP server (https://learn.microsoft.com/api/mcp, no auth). They cover Microsoft products only (Azure, M365, Windows, Entra, Intune, PowerShell, Graph, …) and fail soft if that endpoint is unreachable. Configurable via MS_LEARN_MCP_URL.

Related MCP server: Hoard

Setup

  1. cp .env.example .env and fill in every value (see comments in that file).

  2. Create the schema: paste scripts/schema.sql into the Neon SQL editor (or psql "$DATABASE_URL" -f scripts/schema.sql).

  3. Ingest articles: python scripts/ingest.py scripts/data/kb_dummy_200.json

  4. Run locally: uvicorn server:app --port 8080

Auth

Every /mcp request needs Authorization: Bearer <key> where <key> is listed in MCP_API_KEYS (comma-separated; one key per client, rotate by adding/removing). No keys configured = all requests rejected. /health is open (used by Render health checks).

Deploy (Render)

  1. Push this directory to a GitHub repo.

  2. Render → New → Blueprint → select the repo (render.yaml is picked up automatically).

  3. Fill the sync: false env vars in the Render dashboard (same values as your local .env).

  4. Your MCP endpoint: https://<service>.onrender.com/mcp

Free-tier note: Render spins the service down after idle; first request after idle takes ~30-60s. Fine for testing; use a paid instance for a client-facing demo.

Smoke test

curl https://<service>.onrender.com/health

curl -X POST https://<service>.onrender.com/mcp \
  -H "Authorization: Bearer $KEY" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

This server cannot be installed

F
license - not found
-
quality - not tested
C
maintenance

How are these scores calculated?

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • ragi

    SusuTawar
    A
    license
    A
    quality
    B
    maintenance
    Local-first RAG indexing and semantic search MCP server. Enables document retrieval and context-aware queries using local embedding models.
    3
    9
    MIT

  • porta-rag-mcp

    Ira-Korshunova
    F
    license
    -
    quality
    C
    maintenance
    MCP server exposing a RAG knowledge base as read-only tools (search_knowledge_base, ask_knowledge_base, kb_stats, kb_diagnostic) for AI clients like Claude Desktop and Cursor, enabling token-efficient document retrieval and Q&A.

View all related MCP servers

Related MCP Connectors

  • saagarpatel.dev Portfolio

    Agent-native MCP server over the public saagarpatel.dev corpus. Read-only, stateless.

  • trip2g

    Serve a folder of Markdown notes as an MCP server: hybrid search, reading, and sourced answers.

  • agentdocs-mcp

    MCP server for AgentDocs (agentdocs.eu): read, search, write, comment on & share Markdown docs.

View all MCP Connectors

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/n1khll/kb-rag-mcp'

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