MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
The Documentation Intelligence Layer for AI Coding Agents
npm MIT -
A family of independent, MIT-licensed TypeScript packages for lossless, type-safe document conversion (OOXML, OpenDocument, Markdown, EPUB and PDF) sharing a Zod-based schema layer, plus the CLI, MCP server and web UI built on them.
npm MIT ★ 2 -
MCP server for creating, reading, editing and converting Office documents (docx, xlsx, pptx) — 77 async tools with version history, charts, spell-check, find/replace, and security layers
MIT ★ 1 -
snowflake-atlasgithub.com/sagar-shirwalkar/snowflake-atlasupdated this year
Local-first AI knowledge layer for Snowflake documentation via MCP
Apache-2.0 -
collibra-atlasgithub.com/sagar-shirwalkar/collibra-atlasupdated this year
Local-first AI knowledge layer for Collibra documentation via MCP
Apache-2.0 -
ISO 9001 7.5.3 / ISO 13485 4.2.5 document-control memory for AI agents. Nothing is deleted. EMET 0.3.6 — Enduring Memory & Epistemic Tiers. An MCP memory server with persistent shared memory for AI agents, bot teams and chats: layered memory, verified wri
npm MIT -
safenetai7github.com/Hari-hara7/safenetai7updated this year
A multi-layered cybersecurity platform combining machine learning, real-time Gmail analysis, and community intelligence to detect phishing across URLs, emails, documents, and messaging platforms.
GPL-3.0 -
A transparent knowledge layer across multiple projects via the Model Context Protocol (MCP). Any agent — Claude Code, Claude Desktop, or any MCP-compatible client — connects and gets unified search and navigation across all your documentation.
★ 1 -
FastMCP server providing advanced OCR capabilities with current state-of-the-art models (DeepSeek-OCR, Florence-2, DOTS.OCR, PP-OCRv5, Qwen-Image-Layered decomposition), WIA scanner control, and multi-format document processing for PDFs, CBZ comics, and images.
MIT ★ 25 -
Stackglass is the observability and verification layer for AI-assisted development. Cursor writes and reasons about code. Stackglass gives that agent evidence about state, tests, failures, history, configuration, contracts, and documentation — so it does not have to guess.
NOASSERTION -
Shared context and memory coordination layer for swarms of parallel AI agents. Documented HTTP + WebSocket protocol, interoperable Python and Node CLIs, BM25 keyword memory search, built-in MCP server for agent tool calls.
MIT -
monster-webmcp-servergithub.com/VrilLabs/monster-webmcp-serverupdated this year
👾 MonsterWebMCP server bridges the W3C WebMCP standard (document.modelContext) with the existing MCP ecosystem, enabling any website to expose structured, callable tools to AI agents — natively through the browser’s WebMCP API when available, with seamless fallback to a polyfill-powered transport layer when not.
NOASSERTION ★ 1 -
Workflow and knowledge layer for teams coding with Claude Code. Each session starts with ≤5k chars of repo-scoped context, follows one workflow (orient → grill → epic → build → document), and files every fact where it has a reader: issues, PRs, ADRs/PRDs, a git-backed team wiki, a logbook. CLI + MCP server + two plugins.
MIT ★ 3 -
The canonical 12ui CLI, SDK, MCP server, and visual interface design skills
npm MIT -
@just-every/12uiupdated this year
Node clients for 12ui conversion and private Design Corpus retrieval, plus the conversion CLI and MCP server
npm MIT -
Channel layer that turns any content needing IDP — scans, photos, image PDFs, Office files — into trustworthy structured data (OCR + Markdown + metadata + optional field extraction), exposed via REST / EventBus / MCP. Built on ABP.
LGPL-3.0 ★ 7 -
@iflow-mcp/renefichtmueller-papercortexupdated this year
Self-hosted AI intelligence layer for Paperless-ngx with semantic search, receipt extraction, and MCP Server integration
npm MIT -
A self-hosted, Dockerized MCP server that lets Claude (or any MCP client) create and edit SVG documents using inkex (Inkscape's Python extension library) and render/export them with the real Inkscape CLI.
★ 1 -
Local RAG MCP server for markdown docs. Retrieval only (no answer LLM): ask_docs returns grounded passages plus citations that resolve to real files on disk. Index any local path or git repo, filter by layer, embed offline.
MIT