cran_mcp
MCP server providing up-to-date R package documentation, package metadata, check status, help topics, and R release information directly from CRAN.
README
CRAN MCP
A Model Context Protocol server that provides up-to-date R package documentation, package status information and R release information directly from CRAN.
The server is stateless: it fetches current CRAN data on demand and returns only the relevant information to the MCP client.
Tools
search_packages(query, limit=20)searches all current CRAN package names and short descriptions and ranks matching packages.get_package_info(package)returns the package title, description, current version, CRAN publication date and dependency groups (Depends,Imports,Suggests,LinkingTo,Enhances).get_package_news(package, version=None, max_chars=50000)returns the package NEWS/changelog page from CRAN, optionally restricted to one version such as1.18.4.get_package_check_status(package)returns the current CRAN check status, status counts and results for every check flavor.get_package_topics(package, query=None, limit=100)lists help topics from a CRAN package.get_topic_documentation(package, topic, max_chars=30000)returns one help topic as plain text with its CRAN source URL.search_package_documentation(package, query, limit=10)searches the reference manual and returns matching snippets.get_r_versions(major=None, limit=100)lists R releases available from CRAN, optionally restricted to a major version such as4.get_r_version_news(version, max_chars=50000)returns the official R NEWS section for one R release, for example4.5.1.
Package discovery
search_packages() uses the same machine-readable CRAN package database as tools::CRAN_package_db() in R:
https://cran.r-project.org/web/packages/packages.rds
The RDS database contains the package metadata for current CRAN packages. The search uses Package and Title, where Title is the short package description shown in CRAN's package-by-name list. The RDS file is parsed directly in Python; R is not required at runtime.
Examples:
search_packages("survival model")
search_packages("arrow", limit=10)
R releases
get_r_versions() reads the official CRAN R source directories, so the version list is not hard-coded.
Examples:
get_r_versions()
get_r_versions(major=4)
get_r_version_news("4.5.1")
Local setup
uv sync --dev
uv run cran-mcp
The MCP endpoint is available at http://127.0.0.1:8000/mcp.
Docker
docker build -t cran-mcp .
docker run --rm -p 8000:8000 -e MCP_ALLOWED_HOSTS=localhost,localhost:* cran-mcp
Environment variables
PORT: HTTP port, default8000.MCP_ALLOWED_HOSTS: comma-separated allowed Host values for public deployment.MCP_ALLOWED_ORIGINS: optional comma-separated allowed browser origins.
Examples
search_packages("Bayesian survival")
get_package_info("data.table")
get_package_news("data.table")
get_package_news("data.table", version="1.18.4")
get_package_check_status("data.table")
get_topic_documentation("data.table", "fread")
get_r_versions(major=4)
get_r_version_news("4.5.1")
MCP client
|
| package / R release request
v
CRAN MCP
|
| HTTPS
v
CRAN package database, package pages, NEWS, checks, R source index and HTML reference manuals
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.
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.
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.
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.
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.
E2B
Using MCP to run code via e2b.