AgentIndex icon
AgentIndex
ToolsCategoriesTrendingNewCompareGuides
Submit Tool
ToolsCategoriesTrendingNewCompareGuides
Home/
RAG / Knowledge Base/
anymd
anymd logo

anymd

Active·★ 1.0k·MIT·Updated 2026-10-11

anymd, formerly pdf-reader-mcp, is a Rust MCP server and CLI that converts documents to Markdown on your own machine. It reads PDF, Word, PowerPoint, Excel, EPUB, HTML and web pages, images through OCR, and audio and video through metadata, subtitles and transcripts. The README stresses that nothing is uploaded: OCR uses installed local document VLM models or tesseract, transcripts use ffmpeg and a bundled Qwen3-ASR model, and OCR setup and ASR model downloads need explicit opt-in.

It exposes four MCP tools: `outline` for a heading tree with node ids, `read` to turn a file, URL or folder into Markdown with page ranges, a `max_tokens` budget (default 20000) and a cursor for large documents, `search` across files, folders and URLs in literal or ranked modes, and `inspect` for PDF operations such as rendering pages, extracting regions, OCR and structure with geometry. Output includes `<!-- page 3 -->` citation anchors, a small front-matter header and compact tables, and a layout engine rebuilds reading order for two-column papers and borderless tables.

The README makes speed claims against other converters: 4.58 s in total on 19 benchmark documents against 45.4 s for markitdown and 1,723.3 s for docling. It points to an open AgentDocBench benchmark with per-category scores, including where anymd loses, but these are still the authors' own numbers. Setup is `npx -y @sylphx/anymd setup`, which adds it to MCP clients such as Claude Code, Codex, Cursor, VS Code, Claude Desktop, Windsurf and Gemini CLI, and only needs Node 18+. Licence is MIT and the last push was 2026-10-11. This review is based on the README and repository data; we have not run it ourselves.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool.

#Document Conversion#Markdown Generation#AI Agent Tooling#Local Processing#Multi-format Support#OCR#Rust#CLI
$ Install
$ npm install -g @sylphx/anymd
↗ Visit site★ GitHub
01

Features

01Fast conversion with native Rust.
02Accurate layout and table recovery.
03Token-efficient Markdown output for agents.
04Supports various formats and URLs from a single tool.
05Local and private processing without uploads.
02

Why choose it

+Local and private: no upload and no API key, with local OCR and ASR that need explicit opt-in
+Reads PDF, Office files, EPUB, HTML, images, audio and video in one tool, plus URLs and whole folders
+Four MCP tools with token budget, cursor and citation anchors, built for agent context limits
+One-command setup for many MCP clients; MIT license
03

Trade-offs

!Speed and accuracy comparisons are the authors' own benchmark, even though the corpus and results are published
!OCR and transcription need extra local models or tools, and large downloads, set up by you
!A renamed project, so older pdf-reader-mcp configs need migration
!Reading arbitrary files and URLs is powerful, so restrict where the agent may read
04

Compatibility

Node.js
Runtime
Verified via docs
Rust
Runtime
Verified via docs
Python
Runtime
Verified via docs
Docker
Containerization
Verified via docs
MCP Clients
Integration
Verified via docs
05

Quick start

1
$ npm install -g @sylphx/anymd
06

Use cases

↳Enable AI agents to answer questions from diverse documents like PDFs and spreadsheets.
↳Convert various file formats (PDF, Word, Excel, HTML, etc.) into clean Markdown for AI processing.
↳Perform OCR on image-only documents and generate transcripts for audio/video files.
↳Search across files, folders, and web pages for specific queries.
↳Integrate with AI agent development environments (e.g., Claude Code, Cursor) to augment their document handling.
07

Alternatives

ragflow logo
ragflow★ 92.2k
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
MaxKB logo
MaxKB★ 23.0k
An open-source platform for building enterprise-grade agents. Powerful and easy to use.
Gemini CLI logo
Gemini CLI★ 107.3k
An open-source AI agent that brings the power of Gemini directly into your terminal. Supports native MCP.
letta logo
letta★ 25.1k
Letta is the platform for building stateful agents: open AI with advanced memory that can learn and self-improve over time.
sre logo
sre★ 1.3k
The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular, and production-ready, it lets developers build, run, and manage intelligent agents across local, cloud, and edge environments.
nunu logo
nunu★ 2.6k
A CLI tool for building Go applications.
grafbase logo
grafbase★ 1.2k
The Grafbase GraphQL Federation Gateway
claude-code-guide logo
claude-code-guide★ 4.7k
Master Claude Code with this Guide! Includes: Setup, SKILL.md files, Agents, Commands, workflows and tricks making Claude's potential skyrocket!
See all alternatives →

Featured in these lists

  • Best Tools to Turn PDFs and Office Files into Markdown for AI Agents

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Compatibility05Quick start06Use cases07Alternatives
Stats
GitHub Stars★ 1.0k
Last commit3d ago
StatusActive
LicenseMIT
CategoryRAG / Knowledge Base
Trend (30d)
+0k↑ 3.0%
Links
Documentation↗Discussion↗Issues↗Releases↗

Deploy on DigitalOcean — Get $200 Free Credit

Ad
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

Code AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.