Show HN: MCPShark – Traffic Inspector for Model Context Protocol
https://github.com/mcp-shark/mcp-shark Site: https://mcpshark.sh/
I built MCPShark, a traffic inspector for the Model Context Protocol (MCP).
It sits between your editor/LLM client and MCP servers so you can:
• See all MCP traffic (requests, responses, tools, resources) in one place
• Debug sessions when tools don’t behave as expected
• Optionally run “Smart Scan” checks to flag risky tools / configs First of all, thanks for the contributing to the community. This is a good observability tool to reproduce reasoning paths using structured trace of prompts. During this process, I sometimes do replay the prompts also, especially for some of the use cases where we have observed near deterministic behaviour for some standard prompts. Do you have any plans for adding this feature? Another question: can your architecture scale to thousands of developers & millions of traces? Thank your comments. The primary purpose of this tool is currently for local development. But I would like to hear more about your pain points. Please open a discussion thread https://github.com/mcp-shark/mcp-shark/issues.
Would love to hear more. Why not review the code yourself? Is there any example report that I can review? Thanks.