deepseek-mcp-translator

deepseek-mcp-translator

A local HTTP proxy and MCP server that translates 'developer' role messages to 'system' for DeepSeek API, enabling Android Studio AI plugins to work without errors.

Category
Visit Server

README

DeepSeek Role Translator

HTTP 代理 + MCP 服务器。解决 Android Studio 的 Gemini/Claude 等 AI 插件发送 developer 角色给 DeepSeek API 时报错的问题——自动把 developer 翻译成 DeepSeek 认识的 system。

原理

Android Studio ──(developer)──▶ localhost:8765 ──(system)──▶ api.deepseek.com
Android Studio ◀─────────────────────────────────────────────── api.deepseek.com

代理在本地拦截所有 /v1/chat/completions 请求,把 messages 里的 developer 角色替换成 system,其余字段原样透传。同时暴露 MCP 端点,供 Android Studio 发现和调用。

使用步骤

1. 安装依赖

pip install -r requirements.txt

2. 配置 API Key

复制 .env.example 为 .env,填入 DeepSeek API key 和模型:

DEEPSEEK_API_KEY=sk-your-deepseek-api-key
DEEPSEEK_MODEL=deepseek-v4-pro

模型可选 deepseek-v4-pro 或 deepseek-v4-flash。

3. 启动服务器

双击 run_http.bat,或在终端运行:

python server.py --http

看到以下输出表示启动成功:

代理 + MCP 已启动: http://localhost:8765
  代理端点:     http://localhost:8765/v1
  MCP 端点:     http://localhost:8765/mcp
INFO:     Uvicorn running on http://127.0.0.1:8765

窗口保持开着,不要关。

4. 配置 Android Studio

两步都要做:

① 导入 MCP 配置

Settings → MCP → Import JSON file → 选择项目里的 mcp-config.json。看到 Successfully connected to MCP server DeepSeek Translator 即完成。

② 配置 AI Provider

Settings → AI Provider(或你使用的 AI 插件设置),添加一个新的 provider:

字段 值
URL Schema OpenAI / OpenAI Compatible
Base URL http://localhost:8765/v1
API Key 和 .env 里一样的 DeepSeek key
Model deepseek-v4-pro 或 deepseek-v4-flash

关键:Base URL 必须是 http://localhost:8765/v1,不是 https://api.deepseek.com。这样请求才会经过本地代理做角色翻译。

5. 使用

正常在 Android Studio 里用 AI 聊天即可,角色翻译在后台自动完成,完全无感。

验证

启动服务器后,如果看到终端输出以下日志,说明代理正在工作:

GET /v1/models HTTP/1.1 200 OK
POST /v1/chat/completions HTTP/1.1 200 OK

常见问题

Q: 提示 unknown variant developer?

AI Provider 的 Base URL 没有指向本地代理,还是直连的 DeepSeek。确认 Base URL 是 http://localhost:8765/v1。

Q: 提示 UNAVAILABLE: io exception?

服务器没启动。双击 run_http.bat 启动。

Q: 改了 .env 需要重启吗?

需要。关掉 run_http.bat 窗口,重新打开。

文件结构

├── server.py          # 代理 + MCP 服务器
├── run_http.bat       # Windows 一键启动脚本
├── mcp-config.json    # Android Studio MCP 配置(导入用)
├── requirements.txt   # Python 依赖
├── .env.example       # 配置模板
└── .env               # API key(不提交 git)

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured