Skip to content
MCP server

PdfPecker

Convert HTML and Markdown to PDF with no browser, plus page previews and merging

Runs locallyStatus and history
Pricing
Open source
Platforms
Linux, macOS, Windows
Runs
Locally
Version
1.25.0
Listing updated
3 days ago

About PdfPecker

PdfPecker is an open-source MCP server for files and documents. It runs locally on your machine and is started by your AI client.

PdfPecker for Python is the .NET PdfPecker library compiled ahead of time into a native library inside the wheel, so converting a page does not start a browser or pull in other dependencies. The README reports about 0.7 ms for a one-page invoice on a 4-core Linux VM, against 24 ms for Chromium via Playwright.

The MCP server covers HTML and Markdown to PDF, page previews, PDF text extraction and merging, and the registry says it uses no network. The Python API also converts PDFs to images and files, and the library supports modern CSS, embedded fonts, right-to-left and complex scripts, SVG, barcodes and QR codes, PDF/A and encryption.

Wheels exist for Linux (glibc and musl), macOS and Windows on x64 and ARM64, Python 3.9 and later. The library is MIT licensed.

Install

Run in a terminal

claude mcp add pdfpecker -- uvx pdfpecker

Add to claude_desktop_config.json

{
  "mcpServers": {
    "pdfpecker": {
      "command": "uvx",
      "args": [
        "pdfpecker"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "pdfpecker": {
      "command": "uvx",
      "args": [
        "pdfpecker"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "pdfpecker": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "pdfpecker"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "pdfpecker": {
      "command": "uvx",
      "args": [
        "pdfpecker"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "pdfpecker": {
      "command": "uvx",
      "args": [
        "pdfpecker"
      ]
    }
  }
}

What it does

No browser needed
Own HTML parser, CSS engine, layout and PDF writer.
HTML and Markdown input
CommonMark with GitHub tables and footnotes.
PDF text and images
Extract text or render pages to PNG, JPEG or WebP.
Merging
Combine PDFs from bytes or paths.
Business document features
Page numbers, running headers, PDF/A and encryption.
Broad platforms
Linux, macOS and Windows on x64 and ARM64.

Good for

  • Generate invoices and reports from HTML templates
  • Preview a rendered PDF page as an image
  • Extract text from a PDF
  • Merge several PDFs into one

Pricing

Open source

MIT licensed; free

Prices change. Check pdfpecker.net before you buy.

PdfPecker FAQ

Does it need Chromium?

No. The README says it never starts a browser.

Which Python versions work?

Python 3.9 and later.

What licence?

The library is MIT.

Is it fast?

The README benchmark shows about 0.7 ms for a one-page invoice.

Is PdfPecker free?

Yes. PdfPecker is open source, so you can use and self-host it for free.

How do I add PdfPecker to Claude Code?

Run this command in your terminal: claude mcp add pdfpecker -- uvx pdfpecker

What are the best alternatives to PdfPecker?

The closest alternatives to PdfPecker are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to PdfPecker

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools