Skip to main content
Glama
enesjakozh
kamelirzouni

Deepseek R1 MCP Server

by kamelirzouni
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

Deepseek R1 MCP 서버

Deepseek R1 언어 모델을 위한 모델 컨텍스트 프로토콜(MCP) 서버 구현. Deepseek R1은 8,192개 토큰의 컨텍스트 윈도우를 갖는 추론 작업에 최적화된 강력한 언어 모델입니다.

Node.js를 사용해야 하는 이유는 무엇일까요? 이 구현은 MCP 서버와의 가장 안정적인 통합을 제공하는 Node.js/TypeScript를 사용합니다. Node.js SDK는 더 나은 타입 안전성, 오류 처리 및 Claude Desktop과의 호환성을 제공합니다.

빠른 시작

수동 설치

지엑스피1

Related MCP server: MCP Advanced Reasoning Server

필수 조건

  • Node.js(v18 이상)

  • 엔피엠

  • 클로드 데스크탑

  • Deepseek API 키

모델 선택

기본적으로 이 서버는 deepseek-R1 모델을 사용합니다. DeepSeek-V3를 대신 사용하려면 src/index.ts 의 모델 이름을 수정하세요.

// For DeepSeek-R1 (default)
model: "deepseek-reasoner"

// For DeepSeek-V3
model: "deepseek-chat"

프로젝트 구조

deepseek-r1-mcp/
├── src/
│   ├── index.ts             # Main server implementation
├── build/                   # Compiled files
│   ├── index.js
├── LICENSE
├── README.md
├── package.json
├── package-lock.json
└── tsconfig.json

구성

  1. .env 파일을 만듭니다.

DEEPSEEK_API_KEY=your-api-key-here

  1. Claude Desktop 구성 업데이트:

{
  "mcpServers": {
    "deepseek_r1": {
      "command": "node",
      "args": ["/path/to/deepseek-r1-mcp/build/index.js"],
      "env": {
        "DEEPSEEK_API_KEY": "your-api-key"
      }
    }
  }
}

개발

npm run dev     # Watch mode
npm run build   # Build for production

특징

  • Deepseek R1(8192 토큰 컨텍스트 창)을 사용한 고급 텍스트 생성

  • 구성 가능한 매개변수(max_tokens, 온도)

  • 자세한 오류 메시지를 통한 강력한 오류 처리

  • 전체 MCP 프로토콜 지원

  • Claude Desktop 통합

  • DeepSeek-R1 및 DeepSeek-V3 모델 모두 지원

API 사용

{
  "name": "deepseek_r1",
  "arguments": {
    "prompt": "Your prompt here",
    "max_tokens": 8192,    // Maximum tokens to generate
    "temperature": 0.2     // Controls randomness
  }
}

온도 매개변수

temperature 의 기본값은 0.2입니다.

Deepseek에서는 특정 사용 사례에 따라 temperature 설정할 것을 권장합니다.

사용 사례

온도

예

코딩/수학

0.0

코드 생성, 수학적 계산

데이터 정리/데이터 분석

1.0

데이터 처리 작업

일반 대화

1.3

채팅 및 대화

번역

1.3

언어 번역

창작 글쓰기 / 시

1.5

스토리 쓰기, 시 창작

오류 처리

서버는 일반적인 문제에 대한 자세한 오류 메시지를 제공합니다.

  • API 인증 오류

  • 잘못된 매개변수

  • 속도 제한

  • 네트워크 문제

기여하다

기여를 환영합니다! 풀 리퀘스트를 제출해 주세요.

특허

MIT

Available Tools

1 tool
deepseek_r1C

Generate text using DeepSeek R1 model

ParametersJSON Schema
NameRequiredDescriptionDefault
promptYesInput text for DeepSeek
max_tokensNoMaximum tokens to generate (default: 8192)
temperatureNoSampling temperature (default: 0.2)

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. While 'Generate text' implies a read/write operation that creates content, it lacks critical behavioral details such as rate limits, authentication requirements, response format, error conditions, or whether it's idempotent. The description adds minimal value beyond the basic function.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with a single, clear sentence that directly states the tool's purpose. There's no wasted language or unnecessary elaboration, making it efficiently front-loaded and easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a text generation tool with 3 parameters and no output schema, the description is insufficiently complete. It doesn't explain what kind of text is generated, typical use cases, limitations, or what the return value looks like. The combination of no annotations and no output schema means the description should provide more contextual information than it does.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 100%, meaning all parameters are well-documented in the schema itself. The description adds no additional parameter information beyond what's already in the schema, so it meets the baseline expectation but doesn't provide extra semantic context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Generate text') and specifies the resource ('using DeepSeek R1 model'), which provides a specific verb+resource combination. However, since there are no sibling tools mentioned, there's no opportunity to distinguish from alternatives, preventing a perfect score of 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, prerequisites, or contextual constraints. It simply states what the tool does without any usage instructions, which is insufficient for effective tool selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev1.0.0
    • First observeddeepseek_r1
Deploy Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.1/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of confusion or overlap between tools. The tool's purpose is clearly defined as text generation using the DeepSeek R1 model, leaving no ambiguity for an agent to misselect between multiple options.

Naming Consistency5/5

A single tool inherently exhibits perfect naming consistency, as there are no other tools to compare against. The tool name 'deepseek_r1' follows a clear pattern that matches the server name and describes its function, with no deviations or mixed conventions present.

Tool Count2/5

One tool is too few for a server's apparent scope, as it suggests minimal functionality that might not support complex workflows. While a single tool can be appropriate for very narrow purposes, this server's name implies a broader capability that a single text generation tool does not fully cover, making it feel thin and limited.

Completeness2/5

The tool surface is severely incomplete for the server's implied domain of DeepSeek R1 model interactions. It only offers text generation, lacking obvious gaps such as model configuration, parameter tuning, or other common AI model operations like embeddings or fine-tuning, which could cause agent failures in broader tasks.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches