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.
-
Local CPU OCR for scanned PDFs and images: searchable PDF, structured Markdown, Python API, and MCP. Windows beta.
Apache-2.0 ★ 1 -
Local OCR with Tesseract: turn scans and photos into searchable PDFs on your own computer. Page editing and an MCP server for AI assistants. Linux · Windows · macOS · EN/ES
Apache-2.0 ★ 1 -
pdf2mcpgithub.com/isamba/pdf2mcpupdated this year
Turn any PDF folder into a searchable MCP server
pypi MIT -
FixMyScan remote MCP server and agent skill: turn scanned books into clean, searchable PDFs for e-readers
MIT -
Simple mcp server implementation that converts quantconnect pdfs to md and then makes them searchable. Developed for Claude Desktop.
★ 2 -
distillgithub.com/afly007/distillupdated this year
Self-hosted RAG pipeline — ingest technical PDFs and web pages into a searchable knowledge base, exposed as MCP tools
MIT ★ 2 -
doc-search-mcpgithub.com/nburns/doc-search-mcpupdated this year
Local MCP server that indexes PDFs, EPUBs, HTML, Markdown and text files and makes them searchable by LLM coding agents — keyword (FTS5/BM25), semantic, and hybrid search, entirely on your own machine.
★ 3 -
Searchable toolbox for PDFs, QR codes, configuration diffs, media and background jobs, with browser-local tools, HTTP APIs and MCP.
NOASSERTION -
A private search engine for everything you keep: photos, scans, video, voice notes, chats, email and Office files become searchable PDF/A you can search and ask, offline. OCR, Whisper, CLIP, YOLO and an MCP server in one Rust download.
Apache-2.0 -
Self-hosted RAG-over-MCP server for searchable long-term memory over your markdown/PDF docs — hybrid dense+BM25 retrieval, pluggable embeddings, optional reranking
MIT ★ 2 -
Agent-first research CLI — Exa, Firecrawl, Parallel, Keenable, TinyFish, LlamaCloud plus local PDF/doc tools, a searchable corpus, pipelines and an MCP server in one JSON-first binary. Free tiers work without keys.
npm MIT -
@guqings/exoupdated this year
Your exocortex. Ingest ChatGPT exports, PDFs, and files into a searchable knowledge base. Hybrid FTS5 + vector search. LLM-compiled knowledge pages. MCP server for Claude Code and Cursor.
npm MIT -
resume-mcp-servergithub.com/mnoomnoo/resume-mcp-serverupdated this year
MCP server that gives AI clients structured, searchable access to a local folder of resume files (PDF, DOCX, MD, TXT), exposing tools for querying resumes, work experiences, achievements, skills, side projects, and education.
pypi GPL-3.0 ★ 1 -
Self-hosted document intelligence for RAG — parse, classify, split, and extract from PDF/DOCX/PPTX and images into searchable, cited chunks; query documents and your SQL databases in natural language; serve it all to agents over MCP
pypi MIT -
Self-hosted MCP server that makes your Obsidian/markdown vault searchable — text, PDFs, Office docs, images, audio — from any MCP client. Hybrid retrieval over a typed, governed corpus, sub-second at 50k notes; your files stay plain markdown.
go AGPL-3.0 ★ 9 -
Enterprise-ready vector database toolkit for building searchable knowledge bases from multiple data sources. Supports multi-project management, automatic ingestion from Confluence/JIRA/Git, intelligent file conversion (PDF/Office/images), and semantic search. Includes MCP server for seamless AI assistant integration.
Apache-2.0 ★ 56 -
MTA_Plugingithub.com/GRU953/MTA_Pluginupdated this year
Give any AI assistant a private, token-free memory of your files — Claude, Gemini, Cursor, VS Code, Windsurf, Codex & Grok. Converts attachments (PDF/Office/EPUB/archives) to Markdown and builds a searchable knowledge-graph memory to recall from. 100% local, deterministic, model-free (no LLM/GPU). Incremental & portable; English + Bengali. MIT.
MIT ★ 1 -
NetMap — Network Diagram MCPno update data
Visual network topology editor with AI agent integration via the Model Context Protocol. Open-source successor to netViz (CA Technologies, 1990–2012). Try it live: https://map.den.dance/ What makes it different: • One-click ops dashboard — click any web port (80/443/8080/…) on a node card to open the service in a new tab. Click an SSH port to drop `ssh user@host -p port` into your clipboard AND launch your system SSH handler (Terminal/iTerm/Termius/PuTTY). Your diagram is also your jump host. • AI agents edit the map — 44 MCP tools. Claude / Cursor / Claude Desktop session can build a diagram for you, search across nodes/ports/notes, run smart auto-layouts, export PNG/PDF — all by talking to the open browser tab. • `nmap -oX` import — run a network scan, hand the XML to the agent, get a map with nodes auto-typed from OS fingerprint + port profile (router/switch/firewall/server/printer/…). • CSV inventory import — drop in your asset spreadsheet, auto-detects columns (name/ip/type/ports/notes; aliases like `hostname`/`description` accepted). • Operator-grade node cards — per-node: open ports with service names, Docker services, DNS domains, free-form notes. All searchable cross-entity via the agent. • Smart auto-layout — force-directed (deterministic via seed), cluster-by-type, cluster-by-connection. • Multi-sheet, local-first — multiple maps in one workspace, everything in localStorage. No login, no cloud. Export JSON/PNG/PDF.
smithery -
OCR MCP server for ocr-software.com: let Claude, Cursor and other agents read PDFs and scans
pypi MIT