# openai-mcp-client

> MCP Client

This repository demonstrates using the Model Context Protocol with OpenAI to build a chat-based agent. It provides a starting point for projects, but users should be aware of potential token usage costs.

## Overview

- **Category:** AI
- **Language:** TypeScript
- **Stars:** 53
- **Forks:** 6
- **Owner:** ResoluteError
- **GitHub:** https://github.com/ResoluteError/openai-mcp-client
- **Created:** 2024-12-12T18:19:49+00:00
- **Updated:** 2025-03-27T07:15:09+00:00
- **Source:** https://model-context-protocol.com/clients/openai-anthropic-model-context-protocol-client

## Setup

## Setup

- Ensure Deno v2 is installed
- Run `deno install` to install dependencies
- Copy `.env.example` to `.env` and fill in the values
  - You can choose any MCP server you like - bring your own or use one from the official [MCP server list](https://github.com/modelcontextprotocol/servers/tree/main)
- Run `deno run dev` to start the application

## Tools

## Available Tools

1. Model Context Protocol (MCP) (Used with OpenAI's API to create a simple agent acting from a chat context)
2. OpenAI API (Used to interact with OpenAI models)
3. Tool call responses of type `text` (The implementation supports tool call responses of type `text`)