About Mcp Client Openai
An MCP client service compatible with the OpenAI API format, for users who need to access local MCP servers through a standard OpenAI API interface. It supports stdio and SSE configuration and can connect to OpenAI API-format LLMs that support Function Call.
Key features
- 01OpenAI API format compatibility
- 02API access to local MCP servers
- 03Supports stdio and SSE
- 04Configures LLMs with Function Call
Use cases
- 01Connect local MCP servers to OpenAI API clients
- 02Configure server connections with stdio or SSE
- 03Connect an LLM supporting Function Call
MCP support
It acts as an MCP client service connecting to local MCP servers, with stdio and SSE configuration. Interaction is available through an OpenAI API-compatible interface.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMCP-client
本项目实现了一个兼容 OpenAI API 格式的 MCP (Model Control Protocol) 客户端服务，允许通过标准的 OpenAI API 接口与本地 MCP 模型进行交互。
运行方法：
1, 启动openai api : python main-api.py
2, 启动 stdio cli : python cli.py # just for test
MCP-Server配置：
修改mcp-server-config.json, 支持stdio 和sse两种。
LLM配置：
修改mcp-server-config.json llm字段， 支持所有 OpenAI API 格式的API， 需要支持 Function Call（工具调用）。
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.