DeepSeek

by dmontgomery40

201 10.5k downloads Not rated yet MIT

GitHub Website

About

Integrates DeepSeek's language models, enabling AI-powered chat completions with customizable parameters for tasks like writing assistance and code generation.

Details

Repository: DMontgomery40/deepseek-mcp-server
License: MIT

Explore

- Chat completions with deepseek-v4-flash and deepseek-v4-pro
- FIM (fill-in‑the‑middle) completion with deepseek-v4-pro
- List models and check account balance
- In‑memory conversation history with reset and list tools
- Supports streaming, thinking, reasoning effort, JSON output, and function tools
- Official MCP Registry listing and OCI container image

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below
Plugin Name DeepSeek

Command (node, npx, python, etc.) npx
Arguments
- Argument 1 deepseek-mcp-server
Environment
- DEEPSEEK_API_KEY REPLACE_WITH_DEEPSEEK_KEY
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "deepseek": {
            "env": {
                "DEEPSEEK_API_KEY": "REPLACE_WITH_DEEPSEEK_KEY"
            },
            "args": [
                "deepseek-mcp-server"
            ],
            "command": "npx"
        }
    }
}

JSON

{
    "mcpServers": {
        "deepseek": {
            "env": {
                "DEEPSEEK_API_KEY": "REPLACE_WITH_DEEPSEEK_KEY"
            },
            "args": [
                "/c",
                "npx",
                "deepseek-mcp-server"
            ],
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "deepseek": {
            "env": {
                "DEEPSEEK_API_KEY": "REPLACE_WITH_DEEPSEEK_KEY"
            },
            "args": [
                "deepseek-mcp-server"
            ],
            "command": "npx"
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "deepseek": {
            "env": {
                "DEEPSEEK_API_KEY": "REPLACE_WITH_DEEPSEEK_KEY"
            },
            "args": [
                "deepseek-mcp-server"
            ],
            "command": "npx"
        }
    }
}

JSON

{
    "mcpServers": {
        "deepseek": {
            "env": {
                "DEEPSEEK_API_KEY": "REPLACE_WITH_DEEPSEEK_KEY"
            },
            "args": [
                "/c",
                "npx",
                "deepseek-mcp-server"
            ],
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "deepseek": {
            "env": {
                "DEEPSEEK_API_KEY": "REPLACE_WITH_DEEPSEEK_KEY"
            },
            "args": [
                "deepseek-mcp-server"
            ],
            "command": "npx"
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "deepseek": {
            "env": {
                "DEEPSEEK_API_KEY": "REPLACE_WITH_DEEPSEEK_KEY"
            },
            "args": [
                "deepseek-mcp-server"
            ],
            "command": "npx"
        }
    }
}

JSON

{
    "mcpServers": {
        "deepseek": {
            "env": {
                "DEEPSEEK_API_KEY": "REPLACE_WITH_DEEPSEEK_KEY"
            },
            "args": [
                "/c",
                "npx",
                "deepseek-mcp-server"
            ],
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "deepseek": {
            "env": {
                "DEEPSEEK_API_KEY": "REPLACE_WITH_DEEPSEEK_KEY"
            },
            "args": [
                "deepseek-mcp-server"
            ],
            "command": "npx"
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "deepseek": {
            "env": {
                "DEEPSEEK_API_KEY": "REPLACE_WITH_DEEPSEEK_KEY"
            },
            "args": [
                "deepseek-mcp-server"
            ],
            "command": "npx"
        }
    }
}

JSON

{
    "mcpServers": {
        "deepseek": {
            "env": {
                "DEEPSEEK_API_KEY": "REPLACE_WITH_DEEPSEEK_KEY"
            },
            "args": [
                "/c",
                "npx",
                "deepseek-mcp-server"
            ],
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "deepseek": {
            "env": {
                "DEEPSEEK_API_KEY": "REPLACE_WITH_DEEPSEEK_KEY"
            },
            "args": [
                "deepseek-mcp-server"
            ],
            "command": "npx"
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "deepseek": {
            "env": {
                "DEEPSEEK_API_KEY": "REPLACE_WITH_DEEPSEEK_KEY"
            },
            "args": [
                "deepseek-mcp-server"
            ],
            "command": "npx"
        }
    }
}

JSON

{
    "mcpServers": {
        "deepseek": {
            "env": {
                "DEEPSEEK_API_KEY": "REPLACE_WITH_DEEPSEEK_KEY"
            },
            "args": [
                "/c",
                "npx",
                "deepseek-mcp-server"
            ],
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "deepseek": {
            "env": {
                "DEEPSEEK_API_KEY": "REPLACE_WITH_DEEPSEEK_KEY"
            },
            "args": [
                "deepseek-mcp-server"
            ],
            "command": "npx"
        }
    }
}

From the repository

Run locally via npx deepseek-mcp-server or Docker, setting the DEEPSEEK_API_KEY environment variable. Alternatively, connect to the hosted remote at https://deepseek-mcp.ragweld.com/mcp using a bearer token. Transport is stdio by default; HTTP can be configured via environment variables.

`chat_completion`

DeepSeek V4 chat. Defaults to deepseek-v4-flash. Supports parameters: thinking (object with type enabled or disabled), reasoning_effort (string: low, high, max), JSON output, function tools, logprobs, streaming, and conversation memory.

`create_response`

Stateless native Responses API calls with text or structured input. Supports reasoning effort controls, function tools, server-side web search, structured output, and semantic streaming.

`completion`

DeepSeek V4 Pro FIM completion. Defaults to deepseek-v4-pro.

`list_models`

Reads the live DeepSeek model list.

`get_user_balance`

Reads account balance and availability.

`reset_conversation`

Clears an in-memory conversation.

`list_conversations`

Lists in-memory conversation IDs.

- chat_completion: DeepSeek V4 chat. Defaults to deepseek-v4-flash. Supports thinking: { "type": "enabled" | "disabled" }, reasoning_effort: "low" | "high" | "max", JSON output, function tools, logprobs, streaming, and conversation memory.
- create_response: Stateless native Responses API calls with text or structured input, reasoning effort controls, function tools, server-side web search, structured output, and semantic streaming.
- completion: DeepSeek V4 Pro FIM completion. Defaults to deepseek-v4-pro.
- list_models: Reads the live DeepSeek model list.
- get_user_balance: Reads account balance and availability.
- reset_conversation: Clears an in-memory conversation.
- list_conversations: Lists in-memory conversation IDs.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "deepseek": {
            "env": {
                "DEEPSEEK_API_KEY": "REPLACE_WITH_DEEPSEEK_KEY"
            },
            "args": [
                "deepseek-mcp-server"
            ],
            "command": "npx"
        }
    }
}

Linux

{
    "env": {
        "DEEPSEEK_API_KEY": "REPLACE_WITH_DEEPSEEK_KEY"
    },
    "args": [
        "deepseek-mcp-server"
    ],
    "command": "npx"
}

Macos

{
    "env": {
        "DEEPSEEK_API_KEY": "REPLACE_WITH_DEEPSEEK_KEY"
    },
    "args": [
        "deepseek-mcp-server"
    ],
    "command": "npx"
}

Windows

{
    "env": {
        "DEEPSEEK_API_KEY": "REPLACE_WITH_DEEPSEEK_KEY"
    },
    "args": [
        "/c",
        "npx",
        "deepseek-mcp-server"
    ],
    "command": "cmd"
}

Model Context Protocol server for the current DeepSeek V4 API.

As of August 18, 2026, DeepSeek's public API reference documents:

- POST /chat/completionswithdeepseek-v4-flashanddeepseek-v4-pro
- POST /responseswith native OpenAI Responses API request and response shapes
- POST /beta/completionsfor V4 Pro FIM completion
- GET /models
- GET /user/balance

This server exposes only those documented API surfaces. It does not ship a V4 monitor, speculative image/video/upload tools, or automatic model substitution.

- chat_completion: DeepSeek V4 chat. Defaults todeepseek-v4-flash. Supportsthinking: { "type": "enabled" | "disabled" },reasoning_effort: "low" | "high" | "max", JSON output, function tools, logprobs, streaming, and conversation memory.
- create_response: Stateless native Responses API calls with text or structured input, reasoning effort controls, function tools, server-side web search, structured output, and semantic streaming.
- completion: DeepSeek V4 Pro FIM completion. Defaults todeepseek-v4-pro.
- list_models: Reads the live DeepSeek model list.
- get_user_balance: Reads account balance and availability.
- reset_conversation: Clears an in-memory conversation.
- list_conversations: Lists in-memory conversation IDs.

- URL:https://deepseek-mcp.ragweld.com/mcp
- Auth:Authorization: Bearer <token>

export DEEPSEEK_MCP_AUTH_TOKEN="REPLACE_WITH_TOKEN" codex mcp add deepseek --url https://deepseek-mcp.ragweld.com/mcp --bearer-token-env-var DEEPSEEK_MCP_AUTH_TOKEN

export DEEPSEEK_MCP_AUTH_TOKEN="REPLACE_WITH_TOKEN" claude mcp add --transport http deepseek https://deepseek-mcp.ragweld.com/mcp --header "Authorization: Bearer $DEEPSEEK_MCP_AUTH_TOKEN"

node -e 'const fs=require("fs"),p=process.env.HOME+"/.cursor/mcp.json";let j={mcpServers:{}};try{j=JSON.parse(fs.readFileSync(p,"utf8"))}catch{};j.mcpServers={...(j.mcpServers||{}),deepseek:{url:"https://deepseek-mcp.ragweld.com/mcp",headers:{Authorization:"Bearer ${env:DEEPSEEK_MCP_AUTH_TOKEN}"}}};fs.mkdirSync(process.env.HOME+"/.cursor",{recursive:true});fs.writeFileSync(p,JSON.stringify(j,null,2));'

DEEPSEEK_API_KEY="REPLACE_WITH_DEEPSEEK_KEY" npx -y deepseek-mcp-server

docker pull docker.io/dmontgomery40/deepseek-mcp-server:0.5.0 docker run --rm -i -e DEEPSEEK_API_KEY="REPLACE_WITH_DEEPSEEK_KEY" docker.io/dmontgomery40/deepseek-mcp-server:0.5.0

DEEPSEEK_BASE_URL=https://api.deepseek.com DEEPSEEK_REQUEST_TIMEOUT_MS=120000 DEEPSEEK_DEFAULT_MODEL=deepseek-v4-flash MCP_TRANSPORT=stdio MCP_HTTP_HOST=127.0.0.1 MCP_HTTP_PORT=3001 MCP_HTTP_PATH=/mcp MCP_HTTP_STATEFUL_SESSION=false MCP_HTTP_ALLOWED_ORIGINS=https://app.example.com,http://localhost:3000 CONVERSATION_MAX_MESSAGES=200

MCP_HTTP_ALLOWED_ORIGINSis only needed for browser-based clients. Streamable HTTP requests that send anOriginheader are rejected with403unless the exact origin appears in this comma-separated allowlist; normal MCP clients that omitOriginare unaffected.

npm run build npm test DEEPSEEK_API_KEY="REPLACE_WITH_DEEPSEEK_KEY" npm run test:live DEEPSEEK_MCP_AUTH_TOKEN="REPLACE_WITH_TOKEN" npm run test:remote

The live smoke test performs real DeepSeek requests for model listing, balance, non-thinking chat, thinking streaming chat withreasoning_content, a native Responses API call, FIM completion, and MCP tool calls.

This release uses the supported@modelcontextprotocol/sdkv1 line and the 2025-era MCP initialization flow. Migrating to the split v2 packages and the 2026-07-28 protocol era is intentionally outside this maintenance update because it changes lifecycle and packaging contracts rather than being a drop-in dependency bump.

- MCP Registry name:io.github.DMontgomery40/deepseek
- npm package:deepseek-mcp-server
- OCI package:docker.io/dmontgomery40/deepseek-mcp-server:0.5.0

- DeepSeek chat completions:https://api-docs.deepseek.com/api/create-chat-completion
- DeepSeek Responses API:https://api-docs.deepseek.com/api/create-response
- DeepSeek FIM completions:https://api-docs.deepseek.com/api/create-completion
- DeepSeek models:https://api-docs.deepseek.com/api/list-models
- DeepSeek balance:https://api-docs.deepseek.com/api/get-user-balance
- MCP specification:https://modelcontextprotocol.io/specification/2026-07-28
- MCP TypeScript SDK v2 migration guide:https://github.com/modelcontextprotocol/typescript-sdk/blob/main/docs/migration/upgrade-to-v2.md

Integrate with the Grok AI API to access its powerful language models.

A unified interface to various LLM providers like OpenAI, Anthropic, and Google using Pydantic AI.

Integrate with OpenRouter.ai's diverse ecosystem of AI models. Requires an OpenRouter API key.

A Model Context Protocol (MCP) server that provides access to multiple Large Language Model (LLM) APIs including ChatGPT, Claude, Gemini, and DeepSeek.

The DataFast MCP server lets MCP-compatible clients such as Codex, Claude Code, and Cursor query your analytics and manage your account through natural language.

Atlas Cloud MCP Server (Image / Video / LLM APIs)

A powerful MCP server for AI image, video, and LLM APIs. Integrate models like Seedance and Nano Banana into your workflow with a simple, unified interface powered by Atlas Cloud.

Competitive intelligence platform with 24 tools — monitor competitor pricing, content, positioning, tech stacks, and how ChatGPT, Claude, and Gemini rank your brand.

Integrates Deepseek models with any MCP-compatible client, such as Claude Desktop.

MCP Server for full Easypanel control via Claude Code, Cursor and Claude Desktop.

Advanced text-to-image generation model with superior quality and text rendering via the fal.ai API.

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Explore

Setting up with Highlight

From the repository

chat_completion

create_response

completion

list_models

get_user_balance

reset_conversation

list_conversations

Claude Desktop / Cursor

Linux

Macos

Windows

Atlas Cloud MCP Server (Image / Video / LLM APIs)

Videos about DeepSeek

DeepSeek Harness Setup: Free Claude Code in 10 Minutes

Make DeepSeek BETTER Than Sonnet With Two MCPs (COMPLETELY FREE)

12 - Streamlit as an MCP Host + Ollama DeepSeek MCP Server

More like this

Aws Kb Retrieval Server

GitLab

Context 7

1Panel

`chat_completion`

`create_response`

`completion`

`list_models`

`get_user_balance`

`reset_conversation`

`list_conversations`