Py Mcp Collection

What is Py Mcp Collection?

Py Mcp Collection is a repository containing multiple MCP (Model Context Protocol) servers designed for AI coding assistants. It currently includes three ready-to-use servers—Filesystem Operations, Local References, and MCP Oops—along with others under development.

How to use Py Mcp Collection?

Use the individual MCP servers by following their respective README files for installation and configuration instructions. The README provides links to each server’s detailed documentation.

Key features of Py Mcp Collection

• Filesystem Operations: Bulk file read, preview, search, and summarization.
• Local References: Expose project documentation as best practices.
• MCP Oops: Wrapper to modify other MCP server behavior.
• Doc Store Vector Search: Store and search documents in a vector store (🚧).
• MCP Utils: Library providing utilities for MCP servers (🚧).

Use cases of Py Mcp Collection

• Find relevant files in large codebases using bulk preview and summarization.
• Guide AI coding assistants with project-specific “How To” guides and best practices.
• Modify tool names, descriptions, or add pre/post hooks to existing MCP servers.
• Store and search documentation via vector search for quick retrieval.

FAQ from Py Mcp Collection

Which MCP servers are currently ready to use?

Filesystem Operations, Local References, and MCP Oops are marked as ready (✅). Doc Store Vector Search and MCP Utils are under development (🚧).

What does MCP Oops do?

MCP Oops is a wrapper server that allows you to modify the behavior of another MCP server, such as limiting response sizes, hosting multiple servers on a single port, or changing tool names and descriptions.

What does Filesystem Operations provide?

It performs bulk file and folder operations with centralized exception handling, including reading, previewing, searching, and summarizing code and text to help find relevant files.

How does Local References work?

Local References enables you to expose existing documentation files in your project as “Best Practices” or “How To” guides for an AI coding assistant.