CRAN Package README MCP Server
Fetch comprehensive information about CRAN packages, including READMEs, metadata, and search functionality.
CRAN Package README MCP Server
An MCP (Model Context Protocol) server that enables AI assistants to fetch comprehensive information about CRAN (Comprehensive R Archive Network) packages, including README content, package metadata, and search functionality.
Features
- Package README Retrieval: Fetch formatted README content with usage examples from R/CRAN packages hosted on CRAN repository
- Package Information: Get comprehensive package metadata including dependencies, versions, maintainer information, and documentation
- Package Search: Search CRAN repository with filtering by category, topic, and popularity
- Smart Caching: Intelligent caching system to optimize API usage and improve response times
- GitHub Integration: Seamless integration with GitHub API for enhanced README fetching from package repositories
- Error Handling: Robust error handling with automatic retry logic and fallback strategies
MCP Client Configuration
Add this server to your MCP client configuration:
{
"mcpServers": {
"cran-package-readme": {
"command": "npx",
"args": ["cran-package-readme-mcp-server"],
"env": {
"GITHUB_TOKEN": "your_github_token_here"
}
}
}
}
Note: The
GITHUB_TOKENis optional but recommended for higher API rate limits when fetching README content from GitHub.
Available Tools
get_package_readme
Retrieves comprehensive README content and usage examples for CRAN packages.
Parameters:
{
"package_name": "ggplot2",
"version": "latest",
"include_examples": true
}
package_name(string, required): CRAN package name (e.g., "ggplot2", "dplyr")version(string, optional): Specific package version or "latest" (default: "latest")include_examples(boolean, optional): Include usage examples and code snippets (default: true)
Returns: Formatted README content with installation instructions, usage examples, and function documentation.
get_package_info
Fetches detailed package metadata, dependencies, and maintainer information from CRAN.
Parameters:
{
"package_name": "dplyr",
"include_dependencies": true,
"include_dev_dependencies": false
}
package_name(string, required): CRAN package nameinclude_dependencies(boolean, optional): Include runtime dependencies (default: true)include_dev_dependencies(boolean, optional): Include development dependencies (default: false)
Returns: Package metadata including version info, maintainer details, license, download stats, and dependency information.
search_packages
Searches CRAN repository for packages with filtering capabilities.
Parameters:
{
"query": "machine learning",
"limit": 20,
"category": "MachineLearning"
}
query(string, required): Search terms (package name, description, keywords)limit(number, optional): Maximum number of results to return (default: 20, max: 100)category(string, optional): Filter by package category (Graphics, Statistics, MachineLearning, etc.)
Returns: List of matching packages with names, descriptions, maintainers, and popularity metrics.
Error Handling
The server handles common error scenarios gracefully:
- Package not found: Returns clear error messages with similar package suggestions
- Rate limiting: Implements automatic retry with exponential backoff
- Network timeouts: Configurable timeout with retry logic
- Invalid package names: Validates package name format and provides guidance
- CRAN mirror failures: Fallback strategies when primary CRAN mirror is unavailable
License
MIT
関連サーバー
Scout Monitoring MCP
スポンサーPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
スポンサーAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Artificial Analysis
An unofficial MCP server for the Artificial Analysis API
JFrog MCP Server
Interact with the JFrog Platform API for repository management, build tracking, and release lifecycle management.
@blockrun/mcp
Access 30+ AI models in Claude Code with zero API keys. One wallet, pay-per-request.
Remote MCP Server on Cloudflare
An MCP server deployable on Cloudflare Workers with OAuth login support.
Authless Remote MCP Server
An example of a remote MCP server without authentication, deployable on Cloudflare Workers or runnable locally.
Context Portal MCP (ConPort)
A server for managing structured project context using SQLite, with support for vector embeddings for semantic search and Retrieval Augmented Generation (RAG).
Revit MCP Server
An MCP server for integrating AI with Autodesk Revit, enabling seamless communication via WebSocket.
HeyBeauty
Perform virtual try-ons using the HeyBeauty API.
MCP Android Agent
Automate Android devices using the uiautomator2 library, requiring adb and a connected device.
Gemini MCP
An MCP server that orchestrates Google Gemini and Claude Code models via the OpenRouter API.