Pdf MCP Server

Citra — PDF evidence for agents (Sylphx). Local-first structured text, tables, OCR, visual evidence, citations via MCP/CLI/SDK. Package id

Local serverstdioTypeScript

What is the Pdf MCP server?

Connect Pdf to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Citra — PDF evidence for agents (Sylphx). Local-first structured text, tables, OCR, visual evidence, citations via MCP/CLI/SDK. Package id transitional: @sylphx/pdf-reader-mcp. The pdf mcp server is what makes that connection.

What the server does

Turn PDFs into structured text, tables, OCR, visual evidence, and page-level citations — locally — via SDK, CLI, or MCP.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • Export — @sylphx/pdf-reader-mcp/sdk → Citra (read / search / evidence)
  • Roadmap — ** idiomatic high-level @sylphx/citra package name + richer typed SDK; semantics stay isomorphic with CLI/MCP
  • Doc — Purpose
  • Platform — Native package (auto optionalDependency)
  • read_pdf — Smart default: markdown, tables, structure, OCR, citations
  • search_pdf — Find page + snippet matches before deep reading
  • pdf_evidence — Crops, renders, inspect, focused evidence ops
  • Mode — What it measures
  • persistent_warm — long-lived server, repeated identical local read_pdf after warm-up
  • startup_inclusive — spawn + initialize + one task

Installation

The server ships on npm as @sylphx/pdf-reader-mcp, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Where it fits

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Pdf's toolset — Export, Roadmap, Doc and 7 more — is a fair guide to whether it matches your workflow. It is maintained by shtse8; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Pdf's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 10 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Pdf.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
Export@sylphx/pdf-reader-mcp/sdk → Citra (read / search / evidence)
Roadmap** idiomatic high-level @sylphx/citra package name + richer typed SDK; semantics stay isomorphic with CLI/MCP
DocPurpose
PlatformNative package (auto optionalDependency)
read_pdfSmart default: markdown, tables, structure, OCR, citations
search_pdfFind page + snippet matches before deep reading
pdf_evidenceCrops, renders, inspect, focused evidence ops
ModeWhat it measures
persistent_warmlong-lived server, repeated identical local read_pdf after warm-up
startup_inclusivespawn + initialize + one task

How to install the Pdf MCP server

{
  "mcpServers": {
    "reader-mcp-server-py": {
      "command": "npx",
      "args": ["-y", "@sylphx/pdf-reader-mcp"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Pdf to Export.
  • Use Pdf to Roadmap.
  • Use Pdf to Doc.

Frequently asked questions

It connects Pdf to MCP-compatible AI assistants such as Claude and Cursor, exposing 10 tools (Export, Roadmap, Doc, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Pdf directly.