A
licenseNot graded
qualityC
maintenanceEnables LLM agents to query a structured knowledge library for search, explanations, related concepts, learning paths, examples, and cross-domain references via MCP.
Apache 2.0
lens-serve
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@lens-servewhat verified findings do we have about the payments service?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
lens-serve
The Lens — serve: query the verified library via API + MCP.
The Lens is a neutral, reusable "lab-in-a-box" for systems discovery: you launch a lab (a systems observatory) that reads a system's artifacts, stages candidate findings, has a human verify them, and serves a verified knowledge library.
lens-serve is the serve module — the read side. It exposes the verified
library for query: a read API plus an MCP interface, so people and agents can
ask it questions. It is read-only over verified.
Where it sits
Module | Role |
lens-core | the standard + composition + launcher |
lens-ingest | source material → staged candidate records |
lens-review | human accept/reject/edit → promote to the verified library |
lens-serve (here) | query the verified library (API + MCP) |
lens-observe | signals over activity (active / orphaned / degrading / blind) |
The shared database shape (candidates → decisions → verified, plus lineage and
oversight) is defined in lens-core. This module reads it over an injected
connection (LENS_DB_URL) — never hardcoded.
Related MCP server: kb-mcp-server
Launch (stub)
pip install lens-serve # once published
lens-serve --helpConnection is injected (LENS_DB_URL in your environment) — never hardcoded.
See .env.example.
Identity
This repo has a CHARTER.md — its core directive and its boundary
within The Lens. Read it first. Precedent (how PROVES/Tapestry did it before) is
guidance, not this repo's identity.
Status
Scaffold, 2026-09-26. Neutral/open. No proprietary source data.
The Lens — related repositories
Part of The Lens — a modular, nearly-decomposable kit for systems discovery. Each repo stands on its own; together they compose a lab (a systems observatory).
lens-core — main lab repo: shared standard + composition + launcher + the decomposition method
lens-ingest — intake: source material into staged candidate records
lens-review — review: human accept/reject/edit; promote to the verified library
lens-serve — serve: query the verified library (API + MCP) (this repo)
lens-observe — observe: signals over activity (active / orphaned / degrading / blind)
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues
Related MCP Connectors
Knowledge base MCP for AI agents on iknow.dev. Search, read, and maintain via OAuth.
Make your knowledge agent-ready. One MCP endpoint, 5 connectors, 3 search modes.
Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.
Discover MCP servers, A2A agents, and shared agent knowledge through a read-only MCP gateway.
Related MCP Servers
- FlicenseNot gradedqualityBmaintenanceEnables to build and query a knowledge base with retrieval-augmented generation, supporting document ingestion, hybrid search, and live data integration from external APIs via MCP tools.2-
- AlicenseAqualityBmaintenanceEnables coding agents to query a team knowledge base via MCP, performing semantic search and asking questions that return grounded, citation-backed answers from ingested documents.4MIT
- FlicenseNot gradedqualityCmaintenanceEnables AI agents and users to search a unified organizational knowledge warehouse, create and iterate on documents, manage folders and reviews, and curate shareable knowledge packs through any compatible MCP client.-