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.
-
MCP server and CLI harness for CrewAI-powered semantic PDF search with Qdrant caching.
-
Open-source MCP server bridge for PDF Content Search — full-text PDF search + OCR for Claude/Cursor across thousands of documents.
MIT ★ 1 -
mcp-pdf-chromagithub.com/yourusername/mcp_pdf_chromaupdated this year
MCP server for PDF processing and semantic search with ChromaDB
pypi MIT -
pdf-edit-mcpgithub.com/AryanBV/pdf-edit-mcpupdated this year
MCP server for format-preserving PDF text editing — find, replace, and batch-edit text in existing PDFs while preserving fonts, layout, and visual fidelity. Powered by pdf-edit-engine.
npm MIT ★ 3 -
pdf-toolboxgithub.com/patriciomartinns/pdf-toolboxupdated this year
Expose local PDFs via MCP or the standalone pdf-reader CLI with deterministic chunking, sandboxed access, and semantic search.
MIT ★ 11 -
An MCP server to extraxt/search text from pdf
★ 32 -
pdf-navigator-mcpgithub.com/matsengrp/pdf-navigator-mcpupdated this year
Comprehensive MCP server for PDF reading, navigation, and text search
pypi MIT ★ 9 -
Find files by what's in them: photos, PDFs, docs, voice memos and video, on your own computer. EmbeddingGemma 2 + llama.cpp; CLI, app and MCP server for agents.
MIT ★ 9 -
A Model Context Protocol (MCP) server for indexing and semantically searching PDF research papers
pypi GPL-3.0 ★ 5 -
PDF MCP server with image rendering capabilities. Useful for automatically searching datasheets, manuals, etc...
MIT ★ 82 -
MCP-compatible PDF reading server with intelligent file search and extraction
pypi MIT -
mcp-pdf-servergithub.com/BhagyeshRashinkar/mcp-pdf-serverupdated this year
An MCP server that lets AI assistants query your PDF documents using LLM and Qdrant vector search.
★ 1 -
37 tools to read, create, merge, split, watermark, fill, redact & search PDFs. Local, no API key.
npm -
arxiv-mcp-searchgithub.com/hjh-12138/arxiv-mcp-serverupdated this year
MCP server for arXiv paper search with semantic search, citation enrichment, and PDF extraction
pypi MIT -
MCP server for PDFs in one folder: read, search, render, merge, extract and create from Markdown
cargo Apache-2.0 -
Everyday PDF tools for AI assistants over MCP: read, search, tables, merge, split. Pure Python, zero system dependencies.
MIT -
An MCP (Model Context Protocol) server that provides structured access to ISO 32000 (PDF) specification documents. Enables LLMs to navigate, search, and analyze PDF specifications through well-defined tools.
npm MIT ★ 2 -
Read and edit PDFs on macOS through PDFKit — a local MCP server. Text, search, annotations, forms, redaction. No network.
MIT -
inpdfgithub.com/jonhoo/inpdfupdated this year
A CLI tool and MCP server for searching, navigating, and extracting content from PDFs.
cargo MIT -
Persistent local library for mathematical PDFs: extract once with LaTeX, cache by content hash, search, and query over MCP. Greek and English.
NOASSERTION ★ 1 -
MCP server for Lupa — search your Mac's files by name and document content (PDF, DOCX, XLSX, PPTX, HWP, scanned PDFs via OCR). Korean-aware, ~30ms, fully local.
npm MIT -
Finds broken clause references, undefined terms and other slips in Estonian contracts (Word, PDF, DigiDoc). CLI and MCP server.
NOASSERTION -
nowsecure-mcp-servergithub.com/tatavarthitarun/nowsecure-mcp-serverupdated this year
MCP server for NowSecure Platform: pull remediation findings and generate clean PDF reports, bypassing the broken UI report renderer.
MIT ★ 3 -
@aryanbv/pdf-toolkit-mcpupdated this year
MCP server for PDF manipulation — 22 tools: render pages to images for vision, Markdown/template→PDF, AES-256 encrypt, form-preserving merge/split, fill forms, search, compare, QR codes, watermark. Zero-config, TypeScript-native.
npm MIT -
pdf-rag-mcpgithub.com/MBaranekTech/pdf-rag-mcpupdated this year
MCP server for RAG over messy PDFs — semantic search, OCR, table extraction. Works with Claude Desktop, Claude Code, Cursor, and any MCP client.
MIT -
docsearch-mcpgithub.com/patrickkoss/docsearch-mcpupdated this year
MCP server and CLI tool for local document search with hybrid semantic+keyword search across PDFs, files, and Confluence
npm Apache License Version 2.0 -
annotagithub.com/dengls24/annotaupdated this year
Annota — AI-Powered Paper Annotation MCP Server. Reads PDFs, highlights findings, explains formulas, writes structured notes.
MIT ★ 20 -
Full-text search inside Word, PowerPoint, Excel and PDF - an MCP server backed by SQLite FTS5
mcpb MIT -
OreoLook — an open-source, OpenAI-compatible agentic web search and deep-research engine with streaming, MCP tools, Redis memory, Qdrant retrieval, and PDF exports.
CC0-1.0 ★ 24 -
Local MCP server in Go that indexes Markdown and PDFs and exposes semantic search over Turso — no LLM generation.
-
MCP server for local-first document knowledge bases: LanceDB hybrid search (bge-m3 + CrossEncoder rerank), native BM25 with jieba, and PDF-to-LaTeX ingestion via a local MinerU pipeline
MIT -
MCP server that indexes a local PDF library: full-text and semantic search, snippets and metadata as MCP tools
MIT -
Agentic RAG over one PDF or a whole folder, with page-level evidence to check every answer: hybrid search, selective page reads, tables, OCR, charts, and CJK layouts.
pypi MIT ★ 171 -
零 API Key 即可运行的 Go 版 MCP 搜索服务:多引擎并发(百度/Bing/DDG/Google)+ API 供应商池(Tavily/Exa/豆包/元宝/TinyFish 等)+ 9 大学术引擎 + 网页抓取与 MinerU PDF 解析 + 内置控制中心|Zero-key MCP search server in Go: hybrid engines, provider pool, academic search, web fetch & PDF parsing, built-in dashboard.
go MIT ★ 30 -
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 -
DeepFetchgithub.com/vinay9986/DeepFetchupdated this year
Semantic web search MCP server with Kagi, Scrapfly, PDF extraction, and local ONNX reranking for Claude Desktop, Gemini CLI, and Codex.
Apache-2.0 -
grow-book-mcpgithub.com/dephekt/grow-book-mcpupdated this year
MCP server for semantic search over scanned / image-heavy PDFs: embeds page text AND page renders (Voyage context-4 + multimodal-3.5), fused with BM25.
MIT -
MCP server for Zotero: search and manage your library, add items by DOI, find open access PDFs and insert live Zotero citations into Word documents.
npm NOASSERTION ★ 40 -
Local MCP service for academic research: literature search (Scopus/OpenAlex), citation chains, per-project research memory, paper download and PDF→Markdown conversion via MinerU.
GPL-3.0 -
Dokumen-Pintargithub.com/firdausmntp/Dokumen-Pintarupdated this year
Universal MCP server for document CRUD across formats (TXT, JSON, YAML, CSV, XML, DOCX, XLSX, PPTX, PDF) — with versioning, sandboxed multi-root workspace, full-text search, batch ops, and optional semantic search.
pypi MIT ★ 2 -
puzzletidegithub.com/caravaca-labs/puzzletide-cliupdated this year
Word search generator, crossword generator, and sudoku generator + solver in one local-first CLI — printable PDF puzzle worksheets, themed word banks, verifiable LLM evals, and bundled agent skills.
npm MIT -
parseflow-mcp-servergithub.com/libres-coder/parseflowupdated this year
AI-powered document parsing with 23 tools: PDF (watermark, merge, split), Word, Excel, PowerPoint, OCR, semantic search, and batch processing
npm MIT -
A PDF engine for AI agents: read, search, render, edit and redact PDFs from one binary, as a command or an MCP server
npm AGPL-3.0-or-later -
doc-indexer-mcpgithub.com/eztakesin/doc-indexer-mcpupdated this year
Local document indexer MCP server for semantic search over PDF, Excel, SQL, Markdown, and HTML files using Qdrant and Voyage AI embeddings.
MIT ★ 2 -
专供 AI 智能体访问本地研究文献库的 MCP。支持 PDF、Markdown、BibTeX、RIS、EndNote 及 XML 格式;具备自动索引、智能搜索及只读访问功能。MCP server for AI agents to access local research libraries. Supports PDF, Markdown, BibTeX, RIS, EndNote, XML. Auto-index, smart search, read-only.
MIT ★ 2 -
MCP server for 500Toolbox - Google Search Console, PDF/Office conversion, background removal, AI upscaling, screenshots, DNS/SSL/IP lookups, hashing, QR codes and more, for Claude, Cursor and any MCP client.
npm MIT -
fathom-mcpgithub.com/RomanShnurov/fathom-mcpupdated this year
An MCP server for local file knowledge. Bridges file systems and LLMs using ugrep and poppler-utils to offer full-text search, fuzzy matching, and hierarchical context access for PDFs and codebases, all in a read-only, secure environment.
pypi MIT -
MCP server: convert PDF/DOCX/PPTX/XLSX/EPUB/HTML & scanned docs to clean Markdown — URL-first, keyless, table-preserving, with OCR, split/merge and search. Deployable on Glama.
pypi AGPL-3.0 -
MCP server for local PDFs: read as markdown, text, tables or blocks, search, fill forms. Runs on your machine. AGPL-3.0 or commercial.
pypi AGPL-3.0 -
x402-mcp-serverupdated this year
MCP server for the x402 API Network — screenshot, PDF, crypto sentiment, web scraping, shallow site crawl, file conversion, web search, email, and audio transcription tools with USDC micropayments on Base
npm MIT -
Catch the instructions hidden in a document before your agent follows them. Finds text a model reads but a person cannot see in PDF, DOCX and HTML. CLI, library and MCP server.
Apache-2.0 -
@hanna84/mcp-document-readergithub.com/hannasdev/mcp-document-readerupdated this year
MCP server for AI-assisted PDF reading with pagination, search, and page navigation.
npm MIT -
X Literature MCP — A local, read-only MCP server for academic PDF reading, page rendering, references, and keyword search.
MIT -
docsiftgithub.com/anishmoncivarghese/docsiftupdated this year
Convert documents once. Give agents only what they need — PDFs and Office files to clean Markdown, chunks and local search.
pypi MIT ★ 7 -
Read-only MCP server for Calibre: metadata, BM25 full-text search over EPUB/PDF/MOBI/LIT, chapter/page reading, highlights. Direct SQLite (works with Calibre open), incremental FTS5 index, stdio + Streamable HTTP with bearer auth. Windows-first, cross-platform.
Apache-2.0 ★ 6 -
java-kotlin-mcp-server-prototypegithub.com/wongi-jeong/java-kotlin-mcp-server-prototypeupdated this year
MCP server for PDF semantic search — drop a PDF in MinIO, it's auto-embedded (Ollama + pgvector) and queryable via hybrid vector+keyword retrieval.
MIT -
MCP server exposing direct arXiv/Crossref/Semantic Scholar/Tavily search and PDF full-text extraction as tools.
MIT -
MCP server that gives AI agents (Claude Code, Claude Desktop, Cursor, VS Code, Windsurf) the Lacspace tools: fetch and scrape pages, crawl sites, extract PDF/DOCX/PPTX/EPUB, audit SEO, enrich domains, check uptime and TLS, validate emails, find leads. One
npm SEE LICENSE IN LICENSE -
Local-first MCP server for semantic search over PDF and DOCX documents
★ 1 -
A local evidence workbench for researchers and students: search PDFs and notes, build cited AI context packs, and audit quotations. CLI, browser, and MCP.
MIT ★ 20