OpenAI MCP Client

v1.0.0Coding Agentsstable

A rudimentary implementation of Anthropic's Model Context Protocol with OpenAIs Model

openai-mcp-clientmcpai-integration
Share:
53
Stars
0
Downloads
0
Weekly
0/5

What is OpenAI MCP Client?

OpenAI MCP Client is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to rudimentary implementation of anthropic's model context protocol with openais model

A rudimentary implementation of Anthropic's Model Context Protocol with OpenAIs Model

This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • A rudimentary implementation of Anthropic's Model Context Pr

Use Cases

Model Context Protocol with OpenAI models
ResoluteError

Maintainer

LicenseMIT
Languagetypescript
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx openai-mcp-client

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use OpenAI MCP Client

OpenAI MCP Client is a TypeScript/Deno implementation that bridges Anthropic's Model Context Protocol with OpenAI's API, allowing you to run any MCP server's tools through an OpenAI model as the reasoning backbone. It maintains a running conversation context, detects tool calls from the model's response, executes them against the connected MCP server, and feeds results back into the conversation. Developers use it as a starting point or reference implementation when they want to use OpenAI models as the AI layer in an MCP-powered agentic workflow.

Prerequisites

  • Deno v2 installed (https://deno.land)
  • An OpenAI API key with access to a chat completions model
  • An MCP server to connect to (bring your own or use one from the official MCP servers list)
  • Basic familiarity with TypeScript and the MCP protocol
1

Clone the repository

Clone the openai-mcp-client repository and navigate into the project folder.

git clone https://github.com/ResoluteError/openai-mcp-client.git
cd openai-mcp-client
2

Install Deno dependencies

Use Deno's install command to download and cache all project dependencies declared in deno.json.

deno install
3

Create your .env file

Copy the provided example file and fill in your OpenAI API key and the MCP server command you want to connect to.

cp .env.example .env
4

Configure environment variables

Edit the .env file to set your OpenAI API key, choose a model, and specify the MCP server command. Set DEBUG=true for verbose logging during development.

OPENAI_API_KEY=sk-your-openai-api-key
OPENAI_MODEL=gpt-4o
MCP_SERVER_COMMAND=npx
MCP_SERVER_ARGS=-y,@modelcontextprotocol/server-filesystem,/path/to/directory
DEBUG=false
5

Start the client

Run the development server to launch the OpenAI MCP client and begin interacting via the chat interface.

deno run dev

OpenAI MCP Client Examples

Client configuration

Example .env configuration connecting the OpenAI MCP client to a filesystem MCP server using gpt-4o.

{
  "OPENAI_API_KEY": "sk-your-openai-api-key",
  "OPENAI_MODEL": "gpt-4o",
  "MCP_SERVER_COMMAND": "npx",
  "MCP_SERVER_ARGS": "-y,@modelcontextprotocol/server-filesystem,/tmp/workspace",
  "DEBUG": "false"
}

Prompts to try

Once the client is running with a filesystem MCP server, try these prompts in the chat interface.

- "List all files in the workspace directory"
- "Read the contents of README.md"
- "Create a new file called notes.txt with a summary of our conversation"
- "Search for any TypeScript files that import from 'deno'"
- "What tools are available through the connected MCP server?"

Troubleshooting OpenAI MCP Client

Token costs escalate quickly during long conversations

The full conversation history is sent with every request. For long sessions, restart the client to clear message history, or implement message pruning in src/openai-utils.ts by limiting the messages array length.

Tool call responses from MCP server are ignored or cause errors

This implementation only handles tool call responses of type 'text'. If the MCP server returns resources or other content types, you need to extend the applyToolCallIfExists function in src/openai-utils.ts to handle those types.

MCP server fails to start when the client launches

Verify MCP_SERVER_COMMAND and MCP_SERVER_ARGS in your .env file are correct. Test the MCP server command independently in a terminal to ensure it starts without errors before adding it to the client configuration.

Frequently Asked Questions about OpenAI MCP Client

What is OpenAI MCP Client?

OpenAI MCP Client is a Model Context Protocol (MCP) server that rudimentary implementation of anthropic's model context protocol with openais model It connects AI assistants to external tools and data sources through a standardized interface.

How do I install OpenAI MCP Client?

Follow the installation instructions on the OpenAI MCP Client GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with OpenAI MCP Client?

OpenAI MCP Client works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is OpenAI MCP Client free to use?

Yes, OpenAI MCP Client is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Coding Agents MCP Servers

Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "openai-mcp-client": { "command": "npx", "args": ["-y", "openai-mcp-client"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use OpenAI MCP Client?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides