DeepSeek MCP Server
A server for code generation and completion using the DeepSeek API.
DeepSeek MCP Server
An MCP server implementation that provides code generation and completion capabilities using the DeepSeek API, with support for tool chaining and cost optimization.
Features
- Code generation with language-specific support
- Code completion with context awareness
- Code optimization with multiple targets
- Tool chaining for complex operations
- Built-in caching for cost optimization
- TypeScript implementation with full type safety
Tools
1. generate_code
Generate code using DeepSeek API with language-specific support.
{
"name": "generate_code",
"params": {
"prompt": "Write a function that sorts an array",
"language": "typescript",
"temperature": 0.7
}
}
2. complete_code
Get intelligent code completions based on existing context.
{
"name": "complete_code",
"params": {
"code": "function processData(data) {",
"prompt": "Add input validation and error handling",
"temperature": 0.7
}
}
3. optimize_code
Optimize existing code for performance, memory usage, or readability.
{
"name": "optimize_code",
"params": {
"code": "your code here",
"target": "performance"
}
}
4. execute_chain
Execute a chain of tools in sequence, with context passing between steps.
{
"name": "execute_chain",
"params": {
"steps": [
{
"toolName": "generate_code",
"params": {
"prompt": "Create a REST API endpoint",
"language": "typescript"
}
},
{
"toolName": "optimize_code",
"params": {
"target": "performance"
}
}
]
}
}
Installation
- Clone the repository
- Install dependencies:
npm install
- Build the project:
npm run build
- Configure your DeepSeek API key in the MCP settings file:
{
"mcpServers": {
"deepseek": {
"command": "node",
"args": ["/path/to/deepseek-mcp/build/index.js"],
"env": {
"DEEPSEEK_API_KEY": "your-api-key"
}
}
}
}
Usage
The server can be used with any MCP-compatible client. Here's an example using the MCP CLI:
mcp use deepseek generate_code --params '{"prompt": "Write a hello world program", "language": "python"}'
Tool Chaining
Tool chaining allows you to combine multiple operations into a single workflow. Each tool in the chain can access the results of previous tools through the chain context.
Example chain:
- Generate initial code
- Complete the code with error handling
- Optimize the final result
{
"steps": [
{
"toolName": "generate_code",
"params": {
"prompt": "Create a user authentication function",
"language": "typescript"
}
},
{
"toolName": "complete_code",
"params": {
"prompt": "Add input validation and error handling"
}
},
{
"toolName": "optimize_code",
"params": {
"target": "security"
}
}
]
}
Cost Optimization
The server implements several strategies to optimize API costs:
- Request caching with TTL
- Chain result caching
- Smart prompt construction
- Metadata tracking for usage analysis
Development
To start development:
npm run dev
To clean and rebuild:
npm run rebuild
Requirements
- Node.js >= 18.0.0
- DeepSeek API key
- MCP-compatible client
License
ISC
関連サーバー
Alpha Vantage MCP Server
スポンサーAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
SDK MCP Server
An MCP server providing searchable access to multiple AI/ML SDK documentation and source code.
Compute MCP
An MCP server for evaluating arithmetic expressions using a Pratt parser in Rust.
Hive MCP Server
Provides real-time crypto and Web3 intelligence using the Hive Intelligence API.
DeepView MCP
Enables IDEs like Cursor and Windsurf to analyze large codebases using Gemini's 1M context window.
Modellix Docs
Search the Modellix knowledge base to quickly find relevant technical information, code examples, and API references. Retrieve implementation details and official guides to solve development queries efficiently. Access direct links to documentation for deeper context on specific features and tools.
Gemini MCP Server
An MCP server for interacting with Google's Gemini models through the Gemini CLI.
Vaadin MCP Server
The Vaadin Model Context Protocol (MCP) server provides AI coding assistants with direct access to comprehensive Vaadin documentation, enabling intelligent code assistance for Vaadin Java and React applications.
OpenRouter MCP Client for Cursor
An MCP client for Cursor that uses OpenRouter.ai to access multiple AI models. Requires an OpenRouter API key.
Haldir
Identity, secrets, and audit for AI agents. Proxy mode intercepts every MCP tool call.
ng-diagram MCP Server
Provides ng-diagram documentation and API lookup tools for AI coding assistants.