Prompt analytics for MCP servers(hyprmcp.com)

31 pointsby louis_w_gk10 месяцев назад4 comments

https://hyprmcp.com/blog/mcp-server-prompt-analytics/

5 comments

ripley1210 месяцев назад

Similar approach as MCPCat (telling agents to specify context about why a tool was called in special tool arguments): https://mcpcat.io/

I don't love it (potential privacy issues, and it makes the user's agent spend more tokens), but I don't think there's a better approach right now. Would be great if someone took the time to add an observability mechanism to the MCP spec itself.

pmig10 месяцев назад

After taking a closer look at MCPCat the implementation is quite different for MCPCat you need to integrate a SDK and HyprMCP works as a proxy in front for your already existing MCP server.

pmig10 месяцев назад

The token spend only increases due to the additional parameter names and descriptions, right?

ripley129 месяцев назад

Not just that - for every tool call, the user's agent has to output some extra tokens to put the context info in the additional argument.

huflungdung10 месяцев назад