Skip to main content
Glama
enesjakozh
HarshJ23

DeepSeek-Claude MCP Server

by HarshJ23
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

DeepSeek-Claude MCP サーバー

鍛冶屋のバッジ

DeepSeek R1の高度な推論エンジンを統合することで、 Claudeの推論能力を強化します。このサーバーにより、ClaudeはDeepSeek R1モデルの推論能力を活用して複雑な推論タスクに取り組むことができます。

🚀 機能

高度な推論機能

  • DeepSeek R1 の推論を Claude とシームレスに統合します。

  • 複雑な複数ステップの推論タスクをサポートします。

  • 思慮深い応答を正確かつ効率的に生成できるように設計されています。

Related MCP server: DeepSeek-Claude MCP Server

完全なセットアップガイド

Smithery経由でインストール

Smithery経由で Claude Desktop 用の DeepSeek-Claude を自動的にインストールするには:

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

前提条件

  1. リポジトリのクローンを作成する

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

  2. UVが設定されていることを確認する

    • Windows : PowerShell で以下を実行します。

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

    • Mac : 以下を実行します。

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

  3. 仮想環境を作成する

    uv venv
source .venv/bin/activate

  4. 依存関係をインストールする

    uv add "mcp[cli]" httpx

  5. APIキーの設定

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

  6. MCP サーバーを構成するclaude_desktop_config.jsonファイルを編集して、次の構成を含めます。claude_desktop_config.json ファイル

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

  7. サーバーを実行する

    uv run server.py

  8. テストセットアップ

    • Claude Desktop を再起動します。

    • インターフェースにツール アイコンが表示されていることを確認します。 ツールが見えるツール検証

    • サーバーが表示されない場合は、トラブルシューティング ガイドを参照してください。

🛠 使用方法

サーバーの起動

Claude Desktopと併用すると、サーバーは自動的に起動します。Claude DesktopがMCPサーバーを検出するように設定されていることを確認してください。

ワークフローの例

  1. クロードは高度な推論を必要とする質問を受け取ります。

  2. クエリは処理のために DeepSeek R1 に転送されます。

  3. DeepSeek R1 は、 <ant_thinking>タグで囲まれた構造化推論を返します。

  4. クロードはその推論を最終的な回答に統合します。

📄 ライセンス

このプロジェクトはMITライセンスの下で提供されています。詳細はLICENSEファイルをご覧ください。

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