Skip to main content
Glama
enesjakozh
ygboy1986

DeepSeek-Claude MCP Server

by ygboy1986
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

DeepSeek-Claude MCP Server

Enhance Claude's reasoning capabilities with the integration of DeepSeek R1's advanced reasoning engine. This server enables Claude to tackle complex reasoning tasks by leveraging the reasoning capabilites of deepseek r1 model.

🚀 Features

Advanced Reasoning Capabilities

  • Seamlessly integrates DeepSeek R1's reasoning with Claude.

  • Supports intricate multi-step reasoning tasks.

  • Designed for precision and efficiency in generating thoughtful responses.

Related MCP server: DeepSeek MCP Server

Complete Setup guide

Installing via Smithery

To install DeepSeek-Claude for Claude Desktop automatically via Smithery:

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

Prerequisites

  • Python 3.12 or higher

  • uv package manager

  • DeepSeek API key (Sign up at DeepSeek Platform)

  1. Clone the Repository

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

  2. Ensure UV is Set Up

    • Windows: Run the following in PowerShell:

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

    • Mac: Run the following:

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

  3. Create Virtual Environment

    uv venv
source .venv/bin/activate

  4. Install Dependencies

    uv add "mcp[cli]" httpx

  5. Set Up API Key

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

  6. Configure MCP Server Edit the claude_desktop_config.json file to include the following configuration: claude_desktop_config.json file

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

  7. Run the Server

    uv run server.py

  8. Test Setup

    • Restart Claude Desktop.

    • Verify the tools icon is visible in the interface. tool visible tool verify

    • If the server isn’t visible, consult the troubleshooting guide.

🛠 Usage

Starting the Server

The server automatically starts when used with Claude Desktop. Ensure Claude Desktop is configured to detect the MCP server.

Example Workflow

  1. Claude receives a query requiring advanced reasoning.

  2. The query is forwarded to DeepSeek R1 for processing.

  3. DeepSeek R1 returns structured reasoning wrapped in <ant_thinking> tags.

  4. Claude integrates the reasoning into its final response.

📄 License

This project is licensed under the MIT License. See the LICENSE file for details.

Available Tools

1 tool
reasonA
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

A3.5/5.0
Behavior3/5

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

With no annotations provided, the description carries the full burden. It discloses that the tool uses 'DeepSeek's R1 reasoning engine' with 'advanced reasoning capabilities,' and notes the output format ('enclosed within <ant_thinking> tags'). However, it misses key behavioral traits like performance characteristics (e.g., speed, accuracy), error handling, or any limitations (e.g., input size constraints). It adds some context but is incomplete for a tool with no annotation support.

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 appropriately sized and front-loaded, starting with the core purpose. The first sentence clearly states what the tool does, and subsequent sentences add necessary details about the engine and output format. However, the second sentence about 'advanced reasoning capabilities' could be trimmed as it's somewhat promotional and doesn't add practical value for tool selection.

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 the complexity (reasoning engine with nested input), no annotations, and no output schema, the description is moderately complete. It explains the input structure and output format, but lacks details on error cases, performance, or integration specifics with Claude. For a tool with no structured support, it should do more to cover behavioral aspects and potential pitfalls.

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?

The description adds significant meaning beyond the input schema, which has 0% coverage. It details that the 'query' parameter is a dict with keys 'context' (optional background) and 'question' (specific question to analyze), clarifying the structure and purpose of the nested object. This compensates well for the low schema coverage, though it doesn't cover all potential edge cases or examples.

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 slightly 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 'prepare it for integration with Claude' and the output format, suggesting it's for scenarios where reasoning output needs to be compatible with Claude. However, it lacks explicit guidance on when to use this tool versus alternatives (e.g., other reasoning engines or direct processing), and there are no siblings to compare against. The context is clear but not comprehensive.

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

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.5/5.0
Disambiguation5/5

With only one tool, there is no possibility of confusion or overlap between tools. The single tool 'reason' has a clearly defined and distinct purpose.

Naming Consistency5/5

A single tool cannot demonstrate inconsistency in naming patterns. The tool name 'reason' is clear and descriptive for its function.

Tool Count2/5

One tool is typically too few for a server's purpose unless it's extremely narrow. While the tool is well-described, a single tool feels thin and limits the server's utility for broader reasoning tasks.

Completeness2/5

The server's purpose appears to be reasoning integration, but with only one tool, there are significant gaps. There's no ability to manage sessions, handle different reasoning modes, or provide feedback, making the surface incomplete for practical use.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

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.
    214
    MIT

Appeared in Searches

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ygboy1986/AIClaude'

If you have feedback or need assistance with the MCP directory API, please join our Discord server