Enterprise Internal Knowledge Base: Production-Ready RAG + MCP
This is a reference implementation for enterprise RAG that treats eval scores and observability as first-class CI artifacts. It exposes three MCP primitives: a query tool that hits pgvector with optional reranking, document resources keyed by source_id, and a cite_from_chunks prompt. The real value is the merge gate: every PR runs a 110-question golden set in CI and blocks if top-k recall regresses more than 5pp. Langfuse traces are public and shareable. The corpus is 238 VA education manuals already chunked and embedded in a fixture dump, so you can clone and immediately test prompt changes against known-good baselines. Reach for this when you need a working example of how to stop RAG quality from silently degrading between deploys.
- tool
- 1
- last updated
- Apr 22, 2026
Tools
1 toolsPublic tool metadata for what this MCP can expose to an agent.
queryTools (`query`), Resources (`document://{source_id}`), Prompts (`cite_from_chunks`)
Tools (`query`), Resources (`document://{source_id}`), Prompts (`cite_from_chunks`)
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
Enterprise Internal Knowledge Base — Production-Ready RAG + MCP
A public Retrieval-Augmented Generation pipeline exposed as an MCP server. Sample content from Veterans Affairs education manuals.
The repo implements evaluation, observability, and structure-aware ingestion. Cost/latency tuning, tenant-level access control, and other production concerns are discussed in the article linked below.
📖 Full writeup in Towards AI: Enterprise Internal Knowledge Base RAG MCP: POC-to-Production
Why this exists
RAG demos tend to focus on the quality of the retrieval pipeline, without recognizing that production RAG fails on the next ten steps: prompt or model changes that pass code review but tank answer quality, cost and latency drift that cannot be traced to specific queries, cross-tenant leakage that only surfaces in audit. This repo shows what catching them looks like in practice.
The corpus is public (VA Education manuals — 238 documents, 9,000+ chunks) so anyone can clone, run, and adapt the pipeline.
Quickstart
Details
- Repository
- github.com/kimsb2429/internal-knowledge-base
- Website
- github.com/kimsb2429/internal-knowledge-base
- Categories
- AI & LLM Tools, Documents & Knowledge
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
AgentCrushkristof-sudo/agentcrush-appMarket intelligence for the AI agent economy: rankings, trust signals, liveness. 13 tools.0stars
IBM Code Engine MCP Servermarkusvankempen/code-engine-mcp-serverDeploy to IBM Code Engine from Cursor, Copilot, Claude & Cline. Build, push, deploy via MCP.0stars
VoteShipmattkilmer/voteship-agent-toolkitManage feature requests, votes, roadmaps, and changelogs from any MCP client.0stars
Mercury X402 Mcpmercuryx402/mercury-x402-mcpAgent-payable web data over x402: 18 keyless services an agent pays per call.0stars
OpenClaw Consensusmiconnm/openclaw-consensus-mcp9-LLM consensus + disagreement scoring + cheapest-route picks to fight hallucinations.0stars
Gvnrmightbesaad/gvnrBudget & cost control for AI agents — per-agent spend caps + rate limits before each call.0stars