mcptools and model-context-protocol-resources
About mcptools
posit-dev/mcptools
Model Context Protocol For R
Implements bidirectional Model Context Protocol communication: R can expose functions as tools to MCP clients (Claude Desktop, Copilot) via `mcp_server()` to execute code in live R sessions, or consume third-party MCP servers (GitHub, Google Drive, Confluence) as tools in ellmer chats via `mcp_tools()`. Uses stdio transport to connect MCP-enabled applications with R sessions, enabling AI assistants to access live workspace context and call arbitrary R functions while integrating external tools into R-based chat applications.
About model-context-protocol-resources
cyanheads/model-context-protocol-resources
Exploring the Model Context Protocol (MCP) through practical guides, clients, and servers I've built while learning about this new protocol.
Based on the README, here's a technical summary: Includes 12+ production MCP server implementations (filesystem, Git, GitHub, PubMed, Perplexity, Obsidian) alongside TypeScript/Python client templates and multi-SDK support across TypeScript, Python, Kotlin, Java, and C#. The project provides structured guides for building both MCP clients and servers, establishing a standardized transport layer for AI agents to access external tools and data sources. Targets developers building agentic LLM applications requiring modular, extensible capability integration through the open MCP specification.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work