Skip to main content
Glama
enesjakozh
ruixingshi

Deepseek Thinker MCP Server

by ruixingshi
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

Deepseek Thinker MCP 服务器

铁匠徽章

MCP（模型上下文协议）将 Deepseek 推理内容提供给支持 MCP 的 AI 客户端，例如 Claude Desktop。支持从 Deepseek API 服务或本地 Ollama 服务器访问 Deepseek 的思维过程。

核心功能

  • 🤖双模式支持

    • OpenAI API 模式支持

    • Ollama 本地模式支持

  • 🎯专注推理

    • 捕捉 Deepseek 的思考过程

    • 提供推理输出

Related MCP server: Deepseek MCP Server

可用工具

深入探索思想者

  • 描述：使用Deepseek模型进行推理

  • 输入参数：

    • originPrompt (字符串): 用户的原始提示

  • 返回：包含推理过程的结构化文本响应

环境配置

OpenAI API 模式

设置以下环境变量：

API_KEY=<Your OpenAI API Key>
BASE_URL=<API Base URL>

奥拉玛模式

设置以下环境变量：

USE_OLLAMA=true

用法

与 AI Client 集成，例如 Claude Desktop

将以下配置添加到您的claude_desktop_config.json ：

{
  "mcpServers": {
    "deepseek-thinker": {
      "command": "npx",
      "args": [
        "-y",
        "deepseek-thinker-mcp"
      ],
      "env": {
        "API_KEY": "<Your API Key>",
        "BASE_URL": "<Your Base URL>"
      }
    }
  }
}

使用 Ollama 模式

{
  "mcpServers": {
    "deepseek-thinker": {
      "command": "npx",
      "args": [
        "-y",
        "deepseek-thinker-mcp"
      ],
      "env": {
        "USE_OLLAMA": "true"
      }
    }
  }
}

本地服务器配置

{
  "mcpServers": {
    "deepseek-thinker": {
      "command": "node",
      "args": [
        "/your-path/deepseek-thinker-mcp/build/index.js"
      ],
      "env": {
        "API_KEY": "<Your API Key>",
        "BASE_URL": "<Your Base URL>"
      }
    }
  }
}

开发设置

# Install dependencies
npm install

# Build project
npm run build

# Run service
node build/index.js

常问问题

响应如下：“MCP 错误 -32001：请求超时”

当Deepseek API响应过慢或者推理内容输出过长导致MCP服务器超时时，就会出现此错误。

技术栈

  • TypeScript

  • @modelcontextprotocol/sdk

  • OpenAI API

  • 奥拉马

  • Zod（参数验证）

执照

本项目遵循 MIT 许可证。详情请参阅 LICENSE 文件。

Available Tools

1 tool
get-deepseek-thinkerD

think with deepseek

ParametersJSON Schema
NameRequiredDescriptionDefault
originPromptYesuser's original prompt

TDQS

D1.7/5.0
Behavior1/5

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

No annotations are provided, so the description carries full burden for behavioral disclosure. 'think with deepseek' reveals nothing about whether this is a read/write operation, what permissions are needed, whether it has side effects, rate limits, or what kind of response to expect. It's completely opaque about behavioral characteristics.

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

Conciseness2/5

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

While technically concise with just three words, this is under-specification rather than effective conciseness. The description fails to convey meaningful information, so its brevity is a deficiency rather than a virtue. Every word should earn its place, but here the words don't provide useful content.

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

Completeness1/5

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

For a tool with no annotations and no output schema, the description is completely inadequate. It doesn't explain what the tool does, when to use it, what behavior to expect, or what results it returns. The single parameter is documented in the schema, but the overall context for using this tool is missing entirely.

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?

Schema description coverage is 100%, with the single parameter 'originPrompt' clearly documented as 'user's original prompt'. The description adds no additional parameter information beyond what the schema provides, which is acceptable given the high schema coverage. The baseline of 3 is appropriate when the schema does the documentation work.

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

Purpose2/5

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

The description 'think with deepseek' is a tautology that restates the tool name rather than explaining what the tool actually does. It doesn't specify what resource is being accessed or what operation is performed. While it hints at some thinking/processing function, the purpose remains vague and undefined.

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

Usage Guidelines1/5

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

The description provides absolutely no guidance about when to use this tool, what problems it solves, or what context it's appropriate for. There are no sibling tools mentioned, but even for a standalone tool, this offers no usage context or prerequisites.

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 update
    • First observedget-deepseek-thinker
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

C2.2/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool's purpose is clearly distinct by default.

Naming Consistency5/5

The single tool name 'get-deepseek-thinker' follows a consistent pattern, and with no other tools to compare, there is no inconsistency in naming conventions.

Tool Count2/5

A single tool is too few for most server purposes, as it limits functionality and suggests a thin or incomplete surface. This is borderline for typical server scopes, leaning towards inadequacy.

Completeness1/5

The server's purpose appears to be 'think with deepseek,' but with only one tool, the surface is severely incomplete. There are obvious gaps, such as no way to configure, modify, or manage thinking processes, leading to dead ends for agents.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • MCP Ollama Consult Server

    Atomic-Germ
    A
    license
    B
    quality
    F
    maintenance
    Enables consulting with local Ollama models for reasoning from alternative viewpoints. Supports sending prompts to Ollama models and listing available models on your local Ollama instance.
    5
    1
    MIT

  • Deepseek MCP Server

    arikusi
    A
    license
    A
    quality
    A
    maintenance
    MCP server for DeepSeek AI models (Chat + Reasoner). Supports multi-turn sessions, model fallback with circuit breaker, function calling, thinking mode, JSON output, multimodal input, and cost tracking.
    3
    447 npm
    20
    MIT

  • mcp-server-deepseek

    tizee
    A
    license
    C
    quality
    D
    maintenance
    A Model Context Protocol (MCP) server that provides access to DeepSeek-R1's reasoning capabilities, allowing non-reasoning models to generate better responses with enhanced thinking.
    1
    2
    MIT

Appeared in Searches