Skip to main content

A simplified Python MCP server for reading PDF files, optimized for Amazon Q CLI

Project description

pdf-lite-mcp

CI/CD Pipeline License: MIT Latest Release Python 3.10+ GitHub Issues GitHub Stars

A simplified Python MCP server for reading PDF files, specifically optimized for Amazon Q CLI usage.

Built as a streamlined alternative to complex PDF processing tools, focusing on clean output and reliable performance.

Features

  • Read PDFs from local files or URLs
  • Extract specific pages or full content
  • Metadata extraction (title, author, page count)
  • Batch processing support
  • Security-focused with path validation

Installation

From PyPI (recommended)

# Install using uvx (no need to clone repository)
uvx pdf-lite-mcp

# Or install globally
pip install pdf-lite-mcp

From source

# Install uv
curl -LsSf https://astral.sh/uv/install.sh | sh

# Clone and install
git clone https://github.com/tsaol/pdf-lite-mcp.git
cd pdf-lite-mcp
uv sync

Amazon Q CLI Configuration

Using PyPI package (recommended)

{
  "mcpServers": {
    "pdf-lite": {
      "command": "uvx",
      "args": ["pdf-lite-mcp"],
      "disabled": false,
      "autoApprove": ["read_pdf"]
    }
  }
}

Using local development version

{
  "mcpServers": {
    "pdf-lite": {
      "command": "uv",
      "args": ["run", "python", "src/main.py"],
      "cwd": "/path/to/pdf-lite-mcp",
      "env": {
        "PYTHONPATH": "."
      }
    }
  }
}

Using Git URL

{
  "mcpServers": {
    "pdf-lite": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/tsaol/pdf-lite-mcp.git", "pdf-lite-mcp"],
      "env": {
        "PYTHONPATH": "."
      }
    }
  }
}

Usage

Basic PDF Reading

{
  "tool_name": "read_pdf",
  "arguments": {
    "sources": [{"path": "./document.pdf"}],
    "include_full_text": true
  }
}

Specific Pages

{
  "tool_name": "read_pdf",
  "arguments": {
    "sources": [{"path": "./report.pdf", "pages": [1, 3, 5]}]
  }
}

Multiple PDFs

{
  "tool_name": "read_pdf",
  "arguments": {
    "sources": [
      {"path": "./doc1.pdf"},
      {"url": "https://example.com/doc2.pdf"}
    ]
  }
}

Testing

# Basic tests
uv run python tests/simple_test.py

# Server tests
uv run python tests/test_server.py

# PDF processing tests (requires network)
uv run python tests/test_with_pdf.py

License

MIT License - see LICENSE file for details.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

pdf_lite_mcp-1.0.1.tar.gz (15.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

pdf_lite_mcp-1.0.1-py3-none-any.whl (13.0 kB view details)

Uploaded Python 3

File details

Details for the file pdf_lite_mcp-1.0.1.tar.gz.

File metadata

  • Download URL: pdf_lite_mcp-1.0.1.tar.gz
  • Upload date:
  • Size: 15.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.8.18

File hashes

Hashes for pdf_lite_mcp-1.0.1.tar.gz
Algorithm Hash digest
SHA256 aa5cf75c08d4434a59ef94bf93a533f4d3276afc702d66a8aafb1a3021ba5229
MD5 938313dafd0e083b5c1c860fc21aace2
BLAKE2b-256 9db5956dc83297d0a032c38bcbe05b44e38888177d86e72c068c2c035ed3990f

See more details on using hashes here.

File details

Details for the file pdf_lite_mcp-1.0.1-py3-none-any.whl.

File metadata

File hashes

Hashes for pdf_lite_mcp-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 7baf75ec16845631d2ba86d905611757c9d2c0aaadfb83eaddd19a36bf4080c1
MD5 494474d3b36964fc75300d4ba4ce5424
BLAKE2b-256 c8c039a1b6461ce5230d45fa5f4d08a1f23a011563ffd331282c3cad70802d74

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page