Code-only MCP servers — agent-tools.cloud

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.

@agenson-horrowitz/document-parser-mcp

github.com/agenson-tools/document-parser-mcp
updated this year

Multi-format document parser MCP server - extract text, tables, and metadata from PDFs, images, HTML, and office documents for AI agents

npm MIT
GroupDocs.Parser.Mcp

github.com/groupdocs-parser/GroupDocs.Parser.Mcp
active

GroupDocs.Parser for .NET MCP server — extract text, tables, images, barcodes, and metadata from PDF, Word, Excel, PowerPoint, and image documents via AI agents.

MIT
acikpoz

github.com/gulmezeren2-byte/acikpoz
updated this year

Turkish public construction unit-price (birim fiyat) catalog parser — PDFs into structured pozes. Deterministic, no ML, honest, MCP-native.

MIT ★ 1
pagesift

github.com/YOLOW92/pagesift
active

Self-hosted web scraper, crawler and document parser for AI agents: URLs, PDFs with OCR and Office files to clean Markdown/JSON. Firecrawl- and Jina-compatible API, MCP server, agent endpoint, Python/Node SDKs. Single Rust binary.

npm Apache-2.0 ★ 274
document-fintech-parser-mcp

github.com/Whambammy/document-fintech-parser-mcp
active

Resilient streaming PDF table extraction, high-res page rasterization, AcroForm flattening, and OCR bbox dewarp repair.

MIT
document-reader-mcp

github.com/ifmelate/document-reader-mcp
stale

Universal MCP server for extracting text from various document formats and converts to .md file

MIT ★ 3
doc-indexer-mcp

github.com/eztakesin/doc-indexer-mcp
updated 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
DocSlicer

github.com/DocSlicer/DocSlicer
active

Fast, deterministic document parser and chunker for RAG and agent pipelines. Ships an MCP server for agents navigating long documents with precision.

AGPL-3.0 ★ 36
pdf-table-pull-lite

github.com/tidybytetools/pdf-table-pull-lite
active

Extract tables from PDFs into CSV. Free local CLI and MCP server. No API key.

MIT
superpdf

github.com/arjunprabhulal/superpdf
active

A PDF reader, CLI and MCP server that run on your computer: tables, charts, headings and scans to Markdown, HTML or JSON.

npm Apache-2.0
@superpdf/cli

github.com/arjunprabhulal/superpdf
active

superPDF AI on your computer: PDF tools for Terminal, scripts and AI agents (command-line tool, MCP server and local API)

npm Apache-2.0
Chomper

github.com/IcHiGo-KuRoSaKiI/Chomper
active

Chomper - Chomp through any document. MCP server for parsing 36+ file formats with semantic chunking & TOON token optimization for Claude and AI systems.

MIT ★ 1
pdf-to-text-mcp

github.com/xxx87/pdf-to-text-mcp
stale

A lightweight Model Context Protocol (MCP) server that converts PDF files to text for seamless integration with Cursor IDE and other MCP-compatible applications. Built with TypeScript for reliability and performance.

MIT
docugraph-mcp

github.com/yoiberdev/docugraph-mcp
active

Universal Document Knowledge Graph MCP Server for AI Agents

MIT
canhoto

github.com/luabagg/canhoto
active

Local-first personal finance engine for statement parsing, safe agent workflows, and monthly PDF summaries.

MIT ★ 2
MCP-PDF-Extractor-server

github.com/RayenMalouche/MCP-PDF-Extractor-server
stale

A Java-based server leveraging Apache Tika to extract content and metadata from files (PDF, DOCX, TXT, etc.) in a local files-to-extract directory. Supports HTML (with CSS styling) and text extraction, file listing, and metadata retrieval via MCP-compliant tools and REST APIs. Built with Spring Boot, Jetty, and MCP SDK.
kordoc

github.com/chrisryugj/kordoc
active

한국 문서를 읽고·고치고·새로 쓰는 AI 문서 도구 — HWP·HWPX·PDF·오피스·스캔(OCR)을 Markdown으로, 신구대조·서식 보존 편집·Markdown→HWPX 작성·HWP→HWPX 변환·양식 채우기·공문서 검수까지. 라이브러리·CLI·MCP | Read, diff, edit, write and convert Korean documents (HWP, HWPX, PDF, Office, scans) — library, CLI and MCP server

npm MIT ★ 2,994
mineru-mcp

github.com/GermaniU/mineru-mcp
active

MCP server (HTTP/SSE) that turns PDFs into structured Markdown with MinerU — tables, LaTeX, reading order. Python + FastMCP. Self-hosted, MIT.

MIT ★ 1
mcp-parsekit

github.com/cosmic-api/mcp-parsekit
updated this year

MCP server for ParseKit — document intelligence API for AI agents. Submit any PDF, image, or spreadsheet and get back clean, structured JSON.

npm MIT
antiquarIO

github.com/JCarrascoF/antiquarIO
updated this year

A privacy first (local) document parsing tool and MCP server — convert PDFs and images to structured Markdown using multiple selectable OCR engines. Includes Streamlit GUI and hierarchical chunking for RAG workflows.

MIT
ts-RAG

github.com/guspaz0/ts-RAG
active

Ts RAG system. ingest documents, creates embeddings, stores in pgvector and query through cli or mcp server. fully local with node-llama-cpp

★ 1
ebook-rs

github.com/SV-stark/ebook-rs
active

High-performance, pure Rust multi-format eBook engine (EPUB2/3, MOBI, AZW3, KFX, FB2, LIT,MD,TXT,PDF, CBZ) with native Model Context Protocol (MCP) server, Okapi BM25 AI/RAG chunking, Readium CFI locators, zero-copy search, Python wheels & WASM.

pypi MIT ★ 15
parserail-mcp

github.com/kyisaiah47/parserail-mcp
active

ParseRail is an MCP server that gives Claude, Cursor, and any MCP client native tools to parse documents, extract fields, redact PII, analyze contracts, fight chargebacks, and enrich companies.

npm MIT
free-ocr-api

github.com/Ethos6/free-ocr-api
active

Free self-hosted OCR & document data extraction API. Turn PDFs, scans, invoices, receipts & bank statements into JSON, CSV or Excel. No API keys, no cloud. Web UI, CLI, folder autopilot, MCP server.

MIT ★ 2
study-Tools-mcp-server

github.com/francis-rf/study-Tools-mcp-server
updated this year

AI-powered study assistant built with Model Context Protocol (MCP) - Generate quizzes, flashcards, summaries, and concept explanations from your study materials. Integrates with Claude Desktop and provides a FastAPI web interface.
Skill_Seekers

github.com/yusufkaraaslan/Skill_Seekers
active

Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection

MIT ★ 15,309
filegoblin

github.com/funkyfunc/filegoblin
active

Ingesting the messy world, spitting out clean context. Fast, zero-runtime CLI & MCP server converting PDFs, Office docs, images, audio, and websites into clean Markdown for LLMs.

npm MIT ★ 1
markitdown-rs

github.com/majiayu000/markitdown-rs
active

Convert PDF, Word, Excel, PowerPoint and HTML to Markdown for LLMs and RAG. Rust CLI, Python API and MCP server, with published compatibility tests and benchmarks.

MIT ★ 4
GroupDocs.Total.Mcp

github.com/groupdocs-total/GroupDocs.Total.Mcp
active

GroupDocs.Total for .NET MCP server — single endpoint exposing the combined toolset of all GroupDocs Product - Conversion, Viewer, Markdown, Parser, Comparison, Watermark, Merger, Metadata, Editor, Redaction, Assembly, Search, Signature and Annotation via AI agents.

MIT