Pdf MCP

Surgical PDF access for AI agents: search, read, and extract without flooding context. Its 13 documented tools cover pdf, corpus, info, pages. It runs locally over stdio via the published package.

People connecting media tools to Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-08-24 · ★ 117 · #7 OF 155 MAINTAINED MEDIA · VERIFIED 2026-08-25

MIT · Python servers · how we verify → /methodology

01 · Install Pdf MCP

before you install - you'll need

Set PDF_MCP_AUTH_TOKEN before connecting.

Claude Code

claude mcp add jztan-pdf-mcp -- uvx pdf-mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "jztan-pdf-mcp": {
      "command": "uvx",
      "args": [
        "pdf-mcp"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

pypi package pdf-mcp - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.jztan is GitHub-verified and matches the repo owner

03 · What Pdf MCP can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can read specific pages or ranges, with OCR on demand, tables, and embedded images, read a whole document in one call, byte-capped, and search across a folder, with document and page provenance.

Capability map

Tools grouped from the project's README - what Pdf MCP lets an agent do.

Pdf

12 tools - e.g. Page count, metadata, TOC summary, scanned-page detection. Call first.; Hybrid search (keyword + semantic), page or section granularity, paragraph excerpts with source coordinates; Read specific pages or…

pdf_info · pdf_search · pdf_read_pages · pdf_read_all · pdf_get_toc · pdf_render_pages…

Server

1 tool - e.g. Which optional features and config are active

server_info

Latest releases

v2.2.1 · 2026-08-22

Highlights · OCR results are now cached separately for each language, so switching ocr_lang between calls no longer evicts the previous cache entry and forces re-OCR every time. Case and whitespace differences in the…

v2.2.0 · 2026-08-15

Highlights · Scanned pages finally render legibly. When a page's PNG blows past the transport byte budget, it is now re-encoded as JPEG at the full requested DPI before any resolution is sacrificed. Photographic scans…

v2.1.0 · 2026-08-08

Highlights · pdf-mcp can now run as a remote server. The new pdf-mcp-http entry point is reachable by the Anthropic API MCP connector, fails closed without PDF_MCP_AUTH_TOKEN, binds 127.0.0.1 by default, and refuses to…

04 · Who maintains Pdf MCP

pdf-mcp is maintained by jztan. We track 3 MCP servers from jztan - 3 actively maintained, 189 combined GitHub stars, oldest repo from May 2025. Full record: all servers from jztan.

  1. redmine-mcp-server MCP server that lets AI assistants manage Redmine issues, projects, wikis, and time tracking ★ 69
  2. qt4-doc-mcp-server Offline MCP server for local Qt 4.8, Qt 5, and Qt 6 documentation with full-text search. ★ 3

05 · Facts

category
media - ranked #7 of 155 actively-maintained media servers as of 2026-08-25.
release cadence
10+ releases in the last 90 days (latest 2026-08-22)
registry
io.github.jztan/pdf-mcp (active, first published 2026-02-01 · 25 versions)
packages
pypi:pdf-mcp

06 · Pdf MCP FAQ

Is Pdf MCP still maintained?

Yes - as of 2026-08-25, its last commit was 2026-08-24 and it shipped 10+ releases in the last 90 days. We re-verify nightly.

What can Pdf MCP do?

With this server connected, an agent can read specific pages or ranges, with OCR on demand, tables, and embedded images, read a whole document in one call, byte-capped, and search across a folder, with document and page provenance.

How do I install Pdf MCP?

Run `uvx pdf-mcp`. The README documents one environment variable (PDF_MCP_AUTH_TOKEN) to set first. Set PDF_MCP_AUTH_TOKEN before connecting. You can also paste the ready-made client config above.

Does Pdf MCP run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Pdf MCP