Poe o3 MCP Server

@Anansitrading

Repository

Basic information

About Poe o3 MCP Server

A lightweight MCP server implementation for accessing OpenAI's o3 model via Poe API

#po3-mcp#mcp-server #openai-integration

Poe o3 MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "po3_MCP": {
      "command": "python",
      "args": [
        "-m",
        "venv",
        "venv"
      ]
    }
  }
}

Poe o3 MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Poe o3 MCP Server?

A lightweight Model Context Protocol (MCP) server that provides access to OpenAI's o3 model and other models via Poe's API. It is designed for developers who want to integrate Poe's AI capabilities into any MCP‑compatible application.

How to use Poe o3 MCP Server?

Install prerequisites (Python 3.8+ and a Poe API key), clone the repository, create a virtual environment, install dependencies, set the POE_API_KEY in a .env file, then run python poe_o3_mcp_server.py. The server listens on standard input/output and exposes two tools: o3_query (sends queries to Poe models, defaulting to “o3”) and ping (returns “pong”). Model selection is done by adding a command‑line‑style flag to the prompt (e.g., --Claude-3.5-Sonnet).

Key features of Poe o3 MCP Server

Simple MCP server implementation using FastMCP
Direct integration with Poe’s API for o3 and other models
Model selection via command‑line style flags in prompts
Asynchronous request handling for efficient processing
Comprehensive error handling and logging
Easy setup and configuration

Use cases of Poe o3 MCP Server

Integrate Poe’s AI models into any MCP‑compatible client application
Send queries to the default o3 model or switch to another Poe model via flags
Test server connectivity with the built‑in ping tool
Build custom automation or chatbot systems that use Poe’s API

Frequently asked questions

What are the prerequisites?

Python 3.8+ and a Poe API key, obtainable from [https://poe.com/api_key](https://poe.com/api_key).

How do I select a different model?

Add a flag like `--Claude-3.5-Sonnet` anywhere in the prompt (beginning, middle, or end). The flag is automatically removed before sending the message. If no flag is given, the server defaults to the “o3” model.

What tools does the server expose?

The server provides two tools: `o3_query` (accepts a `message` parameter) and `ping` (no parameters, returns “pong”).

How is the server run?

After installation, execute `python poe_o3_mcp_server.py` from the project directory. The server reads MCP messages from standard input and writes responses to standard output.

Where does my data go and what authentication is used?

Queries are sent to Poe’s API using the API key set in the `POE_API_KEY` environment variable. No local data storage is described. The server communicates via stdin/stdout (stdio transport).

Comments

More Other MCP servers

DeepMark

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

Lemon.io

lemon-io

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3