Data & contentPublic source

mcp-pdf

The PDF Operating Layer for AI Agents

Open the source Read the official guide ↗

What it gives an agent

A purpose-built capability behind one MCP connection.

The server owns its domain logic and publishes a tool contract an MCP client can discover. ADK-Rust can load that contract into an agent, normalize each schema for the chosen model provider, and keep the connection lifecycle outside the agent’s business logic.

Universal PDF coverage — inspect, extract, generate, convert, manipulate, secure, and fill in one binary.

High fidelity — pdf_oxide for extraction (100% pass rate on 3,830 PDFs), printpdf for generation.

Cross-viewer compatible — all output works in Safari, Preview, Chrome, and Acrobat.

Zero system dependencies — pure Rust. No LibreOffice, no Tesseract, no pdfium required.

Local-first — no cloud calls, no API keys, no data leaves your machine.

Registry-ready — ships with mcp-server.toml for automatic ADK-Rust Enterprise onboarding.

Architecture

How mcp-pdf fits into an agent system.

The model never needs the implementation details or credentials of the system behind the server. It sees reviewed tool definitions. The MCP client handles discovery and calls, while the server keeps ownership of validation, policy, and communication with its domain system.

ADK-Rust agent

Chooses a capability from the reviewed tool catalog.

→

MCP client

Discovers schemas, sends calls, and receives typed content.

→

mcp-pdf

Validates the request and owns 57 documented tool contracts.

→

Domain system

Keeps the API, data, credentials, and business rules behind the server.

Connection: stdio · Server framework: rmcp

mcp-pdf architecture diagram from its official repository

Tool catalog

What can an agent ask mcp-pdf to do?

Each tool has a stable name, a human-readable purpose, and a JSON input contract discovered during MCP initialization. Risk classes come from the project’s registry manifest when one is available.

57 named tools

inspect_pdf

Full structural profile (pages, fonts, forms, signatures)

see documentation

classify_pdf

Identify document type (invoice, contract, form, scan)

see documentation

health_check_pdf

Detect corruption, xref errors, broken objects

see documentation

detect_features

Report forms, tags, signatures, JavaScript, embedded files

see documentation

profile_complexity

Rate extraction difficulty (1-5 scale)

see documentation

get_page_count

Number of pages

see documentation

get_info

Quick metadata (pages, size, version, title, author)

see documentation

repair_pdf

Rebuild xref, fix streams, recover corrupted PDFs

see documentation

extract_text

All text from PDF

see documentation

extract_page_text

Text from a specific page

see documentation

extract_metadata

Title, author, dates, creator, producer, XMP

see documentation

extract_tables

Tables as JSON arrays with headers and rows

see documentation

Governance

Understand the effect of every tool.

A server connection inherits the authority of its credentials and deployment environment. The declarations below come from this project’s README and MCP registry manifest; your application still decides which tools an agent receives and where approval is required.

57 see documentation

Encryption — AES-128 R4 with proper O/U value computation (PDF spec compliant)
Redaction — True content removal via lopdf replace_partial_text (not visual masking)
Sanitization — Removes JavaScript, actions, embedded files, metadata in one call
PII scanning — Regex-based detection of emails, phones, SSNs, credit cards

MCP surface

What the current documentation declares.

MCP can carry tools, resources, prompts, structured results, progress, cancellation, and long-running work. This record highlights the modern protocol features explicitly mentioned by this repository.

The current README concentrates on its tool surface. Check the source and release notes before relying on optional MCP capabilities beyond tool discovery and invocation.

rmcpRegistry manifest

Install and connect

Follow the project’s documented starting point.

Install the server in the environment that owns its credentials and domain access. Add it to your MCP host, verify the discovered tools, and narrow the toolset before giving it to a production agent.

Install

cargo install mcp-pdf

MCP client configuration

{
  "mcpServers": {
    "pdf": {
      "command": "mcp-pdf"
    }
  }
}

Commands and configuration are extracted from the public README. Confirm prerequisites, environment variables, and release-specific options in the official documentation before deployment.

Official documentation

Continue with the project maintainers’ source of truth.

This page provides an approachable map of the server. The repository remains authoritative for exact schemas, prerequisites, configuration, examples, tests, releases, and security updates.

Overview ↗README.md Architecture ↗docs/assets/architecture.svg Issues and support ↗github.com issues

Keep exploring