Skip to main content
Glama
enesjakozh
HarshJ23

DeepSeek-Claude MCP Server

by HarshJ23
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

DeepSeek-Claude MCP 服务器

铁匠徽章

通过集成 DeepSeek R1 的高级推理引擎**，增强 Claude 的推理能力**。该服务器利用 deepseek r1 模型的推理能力，使 Claude 能够处理复杂的推理任务。

🚀 功能

高级推理能力

  • 将DeepSeek R1的推理与Claude无缝集成。

  • 支持复杂的多步骤推理任务。

  • 旨在精确、高效地生成深思熟虑的回应。

Related MCP server: DeepSeek-Claude MCP Server

完整的安装指南

通过 Smithery 安装

要通过Smithery自动为 Claude Desktop 安装 DeepSeek-Claude：

npx -y @smithery/cli install @HarshJ23/deepseek-claude-MCP-server --client claude

先决条件

  • Python 3.12 或更高版本

  • uv包管理器

  • DeepSeek API 密钥（在DeepSeek 平台注册）

  1. 克隆存储库

    git clone https://github.com/harshj23/deepseek-claude-MCP-server.git
cd deepseek-claude-MCP-server

  2. 确保紫外线已设置

    • Windows ：在 PowerShell 中运行以下命令：

      powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

    • Mac ：运行以下命令：

      curl -LsSf https://astral.sh/uv/install.sh | sh

  3. 创建虚拟环境

    uv venv
source .venv/bin/activate

  4. 安装依赖项

    uv add "mcp[cli]" httpx

  5. 设置 API 密钥

    Obtain your api key from here : https://platform.deepseek.com/api_keys

  6. 配置 MCP 服务器编辑claude_desktop_config.json文件以包含以下配置：claude_desktop_config.json 文件

    {
    "mcpServers": {
        "deepseek-claude": {
            "command": "uv",
            "args": [
                "--directory",
                "C:\\ABSOLUTE\\PATH\\TO\\PARENT\\FOLDER\\deepseek-claude",
                "run",
                "server.py"
            ]
        }
    }
}

  7. 运行服务器

    uv run server.py

  8. 测试设置

    • 重新启动 Claude Desktop。

    • 验证工具图标在界面中是否可见。 工具可见工具验证

    • 如果服务器不可见，请查阅故障排除指南。

🛠 使用方法

启动服务器

与 Claude Desktop 一起使用时，服务器会自动启动。请确保 Claude Desktop 已配置为检测 MCP 服务器。

示例工作流程

  1. 克劳德收到一个需要高级推理的查询。

  2. 该查询被转发到 DeepSeek R1 进行处理。

  3. DeepSeek R1 返回包裹在<ant_thinking>标签中的结构化推理。

  4. 克劳德将推理融入到最终的回应中。

📄 许可证

本项目遵循 MIT 许可证。详情请参阅LICENSE文件。

Available Tools

1 tool
reasonB
Process a query using DeepSeek's R1 reasoning engine and prepare it for integration with Claude.

DeepSeek R1 leverages advanced reasoning capabilities that naturally evolved from large-scale 
reinforcement learning, enabling sophisticated reasoning behaviors. The output is enclosed 
within `<ant_thinking>` tags to align with Claude's thought processing framework.

Args:
    query (dict): Contains the following keys:
        - context (str): Optional background information for the query.
        - question (str): The specific question to be analyzed.

Returns:
    str: The reasoning output from DeepSeek, formatted with `<ant_thinking>` tags for seamless use with Claude.
ParametersJSON Schema
NameRequiredDescriptionDefault
queryYes

TDQS

B3.3/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the reasoning engine's capabilities and output formatting with tags, but fails to address critical aspects like rate limits, error handling, authentication needs, or performance characteristics. For a tool with no annotation coverage, this leaves significant gaps in understanding its operational behavior.

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

Conciseness4/5

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

The description is well-structured with clear sections for purpose, technical background, parameters, and returns. It avoids unnecessary fluff, but the second sentence about R1's evolution could be trimmed for brevity without losing clarity. Overall, it's efficient and front-loaded with key information.

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

Completeness3/5

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

Given no annotations, no output schema, and a nested parameter structure, the description is moderately complete. It covers the tool's purpose, parameter details, and return format, but lacks information on error cases, performance, or integration specifics. For a tool with such complexity, it should provide more operational context to be fully adequate.

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

Parameters4/5

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

Schema description coverage is 0%, so the description must compensate. It adds meaningful semantics by detailing the 'query' parameter's structure with 'context' and 'question' keys, including that 'context' is optional. This goes beyond the bare schema, providing essential context for parameter usage, though it could specify data types or constraints more explicitly.

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 tool's purpose: 'Process a query using DeepSeek's R1 reasoning engine and prepare it for integration with Claude.' It specifies the verb ('process'), resource ('query'), and technology ('DeepSeek R1'), though it doesn't need to differentiate from siblings since none exist. The purpose is specific but could be more precise about what 'process' entails.

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

Usage Guidelines3/5

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

The description implies usage by mentioning integration with Claude and the reasoning capabilities, but it lacks explicit guidance on when to use this tool versus alternatives. With no sibling tools, this is less critical, but it doesn't provide context on prerequisites, limitations, or ideal scenarios for application.

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 observedreason
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

B3.4/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool named 'reason', there is no possibility of confusion or overlap with other tools. The tool has a single, clearly defined purpose: processing queries through DeepSeek's R1 reasoning engine for Claude integration.

Naming Consistency5/5

A single tool inherently demonstrates perfect naming consistency. The tool name 'reason' follows a clear verb-based pattern appropriate for its function, and there are no other tools to create inconsistency.

Tool Count2/5

A single tool server is generally too minimal for most practical applications. While the tool itself performs a specific reasoning task, the server lacks complementary tools for broader reasoning workflows, making it feel incomplete as a standalone server.

Completeness2/5

The server is severely incomplete for a reasoning engine interface. It provides only query processing without any supporting tools for configuration, history management, different reasoning modes, or result validation. This creates significant gaps that will limit agent effectiveness.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Deepseek-Thinking-Claude-3.5

    niko91i
    A
    license
    B
    quality
    D
    maintenance
    A Model Context Protocol server that combines DeepSeek R1's reasoning capabilities with Claude 3.5 Sonnet's response generation, enabling two-stage AI processing where DeepSeek's structured reasoning enhances Claude's final outputs.
    2
    3
    MIT

  • OpenAI MCP Server

    bhjo0930
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables advanced OpenAI GPT model integration with Claude through 5 specialized tools including GPT-5 reasoning, token optimization, context management, batch processing, and model comparison. Features intelligent fallback mechanisms and task-specific system prompts for enhanced AI capabilities.
    190 npm
    MIT

Appeared in Searches