DeepSeek-MCP
MCP server that enables Claude Code to delegate tasks to DeepSeek and other LLMs, offering 20 tools for code review, analysis, testing, and code generation.
README
🤖 AI Orchestrator MCP Server (DeepSeek & Multi-LLM)
Production-ready Model Context Protocol (MCP) Server for delegating tasks from Claude Code to DeepSeek (deepseek-chat & deepseek-reasoner) and future LLM providers (Gemini, OpenAI, Qwen, Local LLMs).
🌟 Key Features
- Layered Architecture: Decoupled Tools, Router, Merger, Prompt Library, and Provider Abstraction.
- Provider Abstraction: Single unified
AIProviderinterface. Extendable to Gemini, OpenAI, Qwen without modifying tools or Claude Code integration. - DeepSeek Integration: Full support for
deepseek-chatand reasoning modeldeepseek-reasoner. - Parallel Task Execution: Execute concurrent audits (e.g. Code + SQL + Security + Architecture) simultaneously.
- Result Merger Engine: Automatic deduplication, severity prioritization (
CRITICAL->LOW), and unified report generation. - External Prompt Library: Markdown prompt templates stored in
prompts/*.md. - 20 Standalone MCP Tools:
- Review & Analysis (14 Tools):
review_codereview_folderreview_projectreview_sqlreview_architecturereview_securityreview_performancewrite_testsgenerate_seedsummarizedocumentationanalyze_repositoryexplain_coderefactor_code
- Scaffolding & Code Generation (6 Tools):
generate_codegenerate_filesgenerate_sqlgenerate_testsgenerate_documentationgenerate_project
- Review & Analysis (14 Tools):
🚀 Setup & Configuration
1. Installation
npm install
npm run build
2. Configure Environment
Create .env file from .env.example:
DEEPSEEK_API_KEY=your_actual_deepseek_api_key
DEEPSEEK_BASE_URL=https://api.deepseek.com
DEEPSEEK_DEFAULT_CHAT_MODEL=deepseek-chat
DEEPSEEK_DEFAULT_REASONER_MODEL=deepseek-reasoner
DEEPSEEK_REASONING_EFFORT=max
DEFAULT_PROVIDER=deepseek
MAX_PARALLEL_TASKS=5
DEFAULT_TIMEOUT_MS=120000
MAX_RETRIES=3
LOG_LEVEL=info
3. Integration with Claude Code (claude_desktop_config.json or Claude Code config)
Add the following to your MCP settings:
{
"mcpServers": {
"ai-orchestrator": {
"command": "node",
"args": ["c:/Users/User/RiderProjects/DeepSeek-MCP/dist/index.js"],
"env": {
"DEEPSEEK_API_KEY": "your_deepseek_api_key_here"
}
}
}
}
🛠️ Adding a New Provider (e.g. GeminiProvider)
- Create
src/providers/gemini/GeminiProvider.tsimplementingAIProvider. - Register the new provider in
src/providers/index.ts. - Set
DEFAULT_PROVIDER=geminior specify"provider": "gemini"when invoking MCP tools.
No changes to Claude Code or MCP Tool definitions are required!
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.