Odd seeing this right now for me. I recently implemented a 6NF schema for parsed XBRL files from EDGAR. The architecture was the right call... too bad the data is not useful for analytics.

What? No love for Perl scripts in cgi-bin/ ?

In today's world of stupidly fast CPUs and IO a CGI program can be surprisingly performant and effective.

I moved from pip to poetry a while back, but was introduced to uv recently while working on MCP stuff. I now use uv for everything and haven’t looked back.

What made you switch from poetry?

It's coming...

The use case for pg-mcp is server deployment - local running is just for dev purposes. HTTP/SSE enables multiple concurrent connections and network access, which stdio can't provide.

Xata.io looks very interesting!!! I was thinking about building an intelligent agent for pg-mcp as my net project but it looks like you did a lot of the hard work already. When thinking about the "AI Stack" I usually separate concerns like this:

  UI <--> Agent(s) <--> MCP Server(s) <--> Tools/Resources
             |
           LLM(s)

That's very similar to what we are thinking as well, and we'd like to separate the Agent tools into an MCP server as well as use MCP for custom tools.

Indeed. Anything you do with MCP can be done in more traditional ways.

I built this to fill a specific need. It's not really made to talk to Claude Desktop (although it can). It's built to take multiple connections from agents who bring their own LLM (via API key or whatever) and provide context to the LLM model. Yes, it does import the standard Python MCP package, however it does quite a few non-standard things in order to achieve the multi-tenancy. I encourage you to look at the code.

What is multi-tenancy?

Just a fancy way of saying that multiple agents (with their own LLMs) can concurrently connect, also that pg-mcp can simultaneously connect to multiple Postgres servers as well.

User isolation in a single data store. Basically, many customers sharing a single database securely without sharing their data.

I made a few assumptions about the actual deployer and their environment that I shouldn’t have… I’ll need to address this. Thanks!

The pg-mcp server doesn’t need an API key. Those variables are only needed to run the example claude-client. You can write your own agent to talk to whatever LLM you like.