TheAlmanac
Enables programmers to search, download, and access up-to-date API and software documentation through MCP tools, integrating with LLMs like Claude for Desktop.
README
TheAlmanac
A documentation assistant leveraging Model Context Protocol (MCP) to help programmers access the most up-to-date and relevant information from API and software documentation.
Features
- Documentation Crawler: Automatically download and store documentation locally
- Simple Search: Find relevant documentation sections quickly
- MCP Integration: Provide LLMs with tools to access documentation
- File-based Storage: Efficiently organize documentation in a simple file structure
- MCP Server: HTTP server for LLM tool access
Installation
# Clone the repository
git clone https://github.com/yourusername/TheAlmanac.git
cd TheAlmanac
# Install dependencies with UV
uv pip install -e .
Usage
Managing Documentation Sources
# Add a documentation source
almanac add python https://docs.python.org/3/
# List all documentation sources
almanac list
# Download documentation
almanac download python
# Remove a documentation source
almanac remove python
Searching Documentation
# Search all documentation
almanac search "context manager"
# Search a specific source
almanac search "context manager" --source python
# Search with more context
almanac search "context manager" --context-lines 5
Running the MCP Server
# Start the HTTP server (for direct API access)
almanac serve --transport http
# Start the MCP server (for integration with MCP clients like Claude for Desktop)
almanac serve --transport stdio
# Start on a specific host and port (for HTTP transport)
almanac serve --transport http --host 0.0.0.0 --port 9000
MCP Tools
TheAlmanac provides the following MCP tools:
- search_documentation: Search for relevant documentation
- get_documentation: Get a specific document or section
- download_documentation: Download a new documentation source
- list_documentation: List available documentation sources
Example Scripts
The scripts directory contains example scripts for testing and demonstrating TheAlmanac:
test_mcp_tools.py: Directly test MCP toolstest_mcp_server.py: Test the MCP server with HTTP requeststest_mcp_fastmcp.py: Test the FastMCP implementation directlyexample_workflow.py: Run a complete workflow example
Example MCP Tool Usage
# Test the search tool (HTTP server)
./scripts/test_mcp_tools.py search "installation"
# Test getting a specific document (HTTP server)
./scripts/test_mcp_tools.py get python index.md
# Test the search tool (FastMCP)
./scripts/test_mcp_fastmcp.py search "installation"
# Test listing documentation (FastMCP)
./scripts/test_mcp_fastmcp.py list
# Test the complete workflow
./scripts/example_workflow.py
MCP Integration with Claude for Desktop
To integrate TheAlmanac with Claude for Desktop:
-
Make sure Claude for Desktop is installed
-
Edit the Claude for Desktop configuration file:
# For macOS: code ~/Library/Application\ Support/Claude/claude_desktop_config.json -
Add TheAlmanac as an MCP server:
{ "mcpServers": { "the-almanac": { "command": "/path/to/python", "args": [ "-m", "almanac.cli.commands", "serve", "--transport", "stdio" ] } } } -
Restart Claude for Desktop
-
Look for the hammer icon to access TheAlmanac tools
Development
# Install development dependencies
uv pip install -e ".[dev]"
# Run tests
uv run pytest
Adding Dependencies
# Add a production dependency
uv add package_name
# Add a development dependency
uv add --dev package_name
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.