# openai-compat-mcp

> openai-compat-mcp — zjukop3-openai-compat-mcp. Use this tool when you need to integrate OpenAI-compatible APIs with Model Context Protocol (MCP) clients, such as Claude Desktop and Cursor, to enable seamless communication and functionality. It bridges various APIs, including DeepSeek, Zhipu, Qwen, Moonshot, and vLLM, into a unified MCP server. This tool is ideal for developers seeking to expand MCP client capabilities with diverse AI models.

Canonical page: https://skillsregistry.net/skills/zjukop3-openai-compat-mcp  
JSON: https://api.skillsregistry.net/v1/skills/zjukop3-openai-compat-mcp

## Description

Bridge any OpenAI-compatible API (DeepSeek / Zhipu / Qwen / Moonshot / vLLM) into a Model Context Protocol server for Claude Desktop, Cursor and other MCP clients.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-10-11

## Source

- **Source listing:** [GitHub](https://github.com/zjukop3/openai-compat-mcp)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "zjukop3-openai-compat-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/zjukop3-openai-compat-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/zjukop3-openai-compat-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt