Skip to main content

Enhanced MCP server for searching documentation with OSINT vulnerability scanning, security analysis, and AWS-style deployment

Project description

Documentation Search MCP Server

This Model Context Protocol server delivers documentation search, vulnerability auditing, and project bootstrapping in one place. It runs as a long-lived process that serves requests from MCP-compatible clients such as Claude Desktop or Cursor.

Core Capabilities

  • Aggregate semantic search across 100+ documentation sources.
  • Scan local Python projects for dependency vulnerabilities.
  • Generate starter scaffolds (FastAPI, React) and developer environment files.
  • Provide learning paths, curated code examples, and library comparisons on demand.

Quick Start

# Requires Python 3.12+
uvx documentation-search-enhanced@latest

Configure your assistant to launch the server:

{
  "mcpServers": {
    "documentation-search-enhanced": {
      "command": "uvx",
      "args": ["documentation-search-enhanced@latest"],
      "env": { "SERPER_API_KEY": "your_serper_api_key_here" }
    }
  }
}

The process stays running and listens for JSON-RPC calls; stop it with Ctrl+C when finished.

Codex CLI

Add the server using Codex’s built-in MCP manager:

codex mcp add documentation-search-enhanced \
  --env SERPER_API_KEY=your_serper_api_key_here \
  -- uvx documentation-search-enhanced@latest

To run from a local checkout instead:

codex mcp add documentation-search-enhanced \
  --env SERPER_API_KEY=your_serper_api_key_here \
  -- uv run python src/documentation_search_enhanced/main.py

Development Workflow

git clone https://github.com/antonmishel/documentation-search-mcp.git
cd documentation-search-mcp
uv sync --all-extras --all-groups  # include dev tools
echo "SERPER_API_KEY=your_key_here" > .env
uv run python src/documentation_search_enhanced/main.py
  • Run core tests: uv run pytest --ignore=pytest-test-project.
  • Run example FastAPI tests: cd pytest-test-project && uv run --all-extras python -m pytest -q.
  • Lint: uv run ruff check src. Format: uv run black src (use --check to verify).
  • Build distributions via uv build; publish_to_pypi.sh wraps the release flow.

Configuration

Ask your assistant for the current configuration via the get_current_config tool, save it as config.json, then adjust sources or caching preferences. Validate changes locally with uv run python src/documentation_search_enhanced/config_validator.py. Keep secrets in .env rather than committing them.

Tools at a Glance

Key MCP tools include get_docs, semantic_search, get_learning_path, get_code_examples, scan_project_dependencies, generate_project_starter, manage_dev_environment, get_security_summary, and compare_library_security.

Contributing & License

Start with the contributor guide in AGENTS.md plus the workflow details in CONTRIBUTING.md. Follow Conventional Commits, document validation steps in pull requests, and update CHANGELOG.md for user-facing adjustments. Released under the MIT License—see LICENSE for the full text.

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

documentation_search_enhanced-1.4.1.tar.gz (53.9 kB view details)

Uploaded Source

Built Distribution

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

documentation_search_enhanced-1.4.1-py3-none-any.whl (59.9 kB view details)

Uploaded Python 3

File details

Details for the file documentation_search_enhanced-1.4.1.tar.gz.

File metadata

File hashes

Hashes for documentation_search_enhanced-1.4.1.tar.gz
Algorithm Hash digest
SHA256 b9e69a2110a95cb19a61af64298ec5d809ef7fb0468b7c64113c63d90f3e0952
MD5 9ae843bc37fe549925cdad8e90513175
BLAKE2b-256 0234b2e16e95d57e74ee5c0e71b87b2b49dfadcfc18c731312ade232653eca2e

See more details on using hashes here.

File details

Details for the file documentation_search_enhanced-1.4.1-py3-none-any.whl.

File metadata

File hashes

Hashes for documentation_search_enhanced-1.4.1-py3-none-any.whl
Algorithm Hash digest
SHA256 21341ed8728fd28a86b8d2344db7f92f1152a998a88fb9b51d9b2427bd8fd011
MD5 50256f9fe7c6b8895f694052ad9c632a
BLAKE2b-256 e1edc2d128bbb1ec0ca4038e27bf0b8aea05e29483158028ff9a0c93f5807aaf

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