Post

Not sure how useful it is yet, but parsing PageFind indexes in C# was a fun kata. Built a .NET MCP Server for AI agents to search PageFind indexes, locally or online. Demo: list indexes, search my blog & fetch page. Open source & on @nuget.org: www.nuget.org/packages/pfmcp #dotnet #mcp #pagefind

nice, no crawler needed since the site already builds the index.

Yip, and works locally too, so i.e. my static documentation site can have its index on disk for lower latency / offline knowledge. Potentially it could save tokens.

does the agent search the index through a tool, or load the whole file?