DeepSeek

Community

dmontgomery40

Model Context Protocol server for DeepSeek's advanced language models

Publisher	dmontgomery40
Repository	`deepseek-mcp-server`
Language	TypeScript
Forks	52
Stars	334
Available tools	0
Transport type	stdio
Categories	AI Ml
License	MIT
Links	GitHub Homepage

Connect tools to AI workflows
DeepSeek exposes MCP capabilities that can be used by compatible AI clients and agents.
0 available tools
Browse the callable actions below, including names and descriptions when provided by the server.
Ready-to-copy setup
Use the installation snippets to configure this server in your preferred MCP client.
Open source signals
334 stars and 52 forks from the linked repository.

DeepSeek MCP Server

Model Context Protocol server for the current DeepSeek V4 API.

As of April 24, 2026, DeepSeek's public API reference documents:

POST /chat/completions with deepseek-v4-flash and deepseek-v4-pro
POST /beta/completions for 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.

Tools

chat_completion: DeepSeek V4 chat. Defaults to deepseek-v4-flash. Supports thinking: { "type": "enabled" | "disabled" }, reasoning_effort: "high" | "max", JSON output, function tools, logprobs, streaming, and conversation memory.
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.

Hosted Remote

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

Codex CLI:

bash
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

Claude Code:

bash
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"

Cursor:

bash
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));'

Local Stdio

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

Docker:

bash
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

Environment

Required:

bash
DEEPSEEK_API_KEY=your-api-key

Optional:

bash
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
CONVERSATION_MAX_MESSAGES=200

Verification

bash
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 with reasoning_content, FIM completion, and MCP tool calls.

Registry Identity

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

Official References

DeepSeek chat completions: https://api-docs.deepseek.com/api/create-chat-completion
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/2025-11-25

License

MIT

Installation

TypingMind

Prerequisites:

Node.js 18+

{
  "mcpServers": {
    "deepseek": {
      "command": "npx",
      "args": [
        "-y",
        "deepseek-mcp-server"
      ],
      "env": {
        "DEEPSEEK_API_KEY": "your-api-key"
      }
    }
  }
}

Use DeepSeek MCP with multiple AI models

TypingMind connects MCP tools at the workspace level, so once DeepSeek is connected, you can use it with different AI models in TypingMind instead of setting it up separately for each model. This MCP runs locally through the TypingMind MCP connector on your device.

Setup guide to use the local connector

Use this when the MCP server needs access to local files, apps, or private resources on your computer.

Open the MCP settings

In TypingMind, go to Settings, Advanced Settings, then Model Context Protocol and choose Setup Connector.

Open TypingMind in your browser.
Click the Settings icon.
Go to Advanced Settings.
Open the Model Context Protocol section.
Click Setup Connector and choose This Device.

TypingMind MCP connector setup screen with This Device selected

Run the connector command

Choose This Device, copy the command from TypingMind, and run it in Terminal. Keep the process running while you use MCP.

Copy the setup command shown by TypingMind.
Open Terminal on macOS or Windows Terminal on Windows.
Paste and run the command.
Approve the package install if Terminal asks you to proceed.
Keep the Terminal window running while using MCP tools.

Add DeepSeek as a server

When the connector status is Ready, click Edit Servers and paste the MCP server configuration.

Wait until the connector status shows Ready.
Click Edit Servers.
Paste the DeepSeek MCP server configuration.
Save the server list.
Refresh if you want to confirm the connector is still ready.

TypingMind MCP settings showing active server and Edit Servers button

Use it across models

Save the server list, open Plugins, enable the DeepSeek MCP tools, then select any supported AI model in TypingMind and use the tools in chat or assign them to an AI agent.

Open the Plugins page in TypingMind.
Enable the DeepSeek MCP tools.
Start a chat and choose the AI model you want to use.
Use the MCP tools in chat or assign them to an AI agent.
Switch to another AI model whenever needed without reconnecting MCP.

TypingMind chat using enabled MCP tools with a selected AI model

Frequently asked questions

What is the DeepSeek MCP server used for?

DeepSeek is an MCP server that lets compatible AI clients connect to external tools and context. In TypingMind, you can add this MCP server once and make its tools available in your AI workspace.

Can I use DeepSeek MCP with multiple AI models in TypingMind?

Yes. TypingMind connects MCP tools at the workspace level, so you can use DeepSeek with different AI models such as Claude, ChatGPT, Gemini, or other models you have configured in TypingMind without setting up the MCP server separately for each model.

Why use DeepSeek MCP with TypingMind?

TypingMind is one of the best frontends for LLM chat because it brings multiple AI models, prompts, plugins, AI agents, API keys, and MCP tools into one workspace. With DeepSeek connected, you can use its MCP tools across your preferred models while keeping your chat workflow organized in TypingMind.

How do I connect DeepSeek MCP to TypingMind?

DeepSeek runs through the TypingMind local MCP connector. This is best when the MCP server needs access to local files, desktop apps, command-line tools, or private resources on your computer.

What tools does DeepSeek MCP provide in TypingMind?

DeepSeek exposes MCP capabilities that can be enabled from the TypingMind Plugins page and used in chat or assigned to AI agents.

Do I need to share my API keys with TypingMind to use DeepSeek MCP?

No. TypingMind is local-first and lets you keep your model providers, API keys, prompts, and MCP configuration under your control. If DeepSeek requires authentication, add the required headers, OAuth settings, or local configuration for that MCP server when you create the connection.

Related MCP Servers

View all

Knowledge Graph Memory

modelcontextprotocol

OrganizationPopular

Model Context Protocol Servers

Context7

Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

Blender

Experience seamless AI-powered 3D modeling by connecting Blender with Claude AI via the Model Context Protocol. BlenderMCP enables two-way communication, allowing you to create, modify, and inspect 3D scenes directly through AI prompts. Control objects, materials, lighting, and execute Python code in Blender effortlessly. Access assets from Poly Haven and generate AI-driven models using Hyper3D Rodin. This integration enhances creative workflows by combining Blender’s robust tools with Claude’s intelligent guidance, making 3D content creation faster, interactive, and more intuitive. Perfect for artists and developers seeking AI-assisted 3D design within Blender’s environment.

Google GenAI Toolbox

MCP Toolbox for Databases is an open source MCP server for databases.

DeepSeek MCP Server

Tools

Hosted Remote

Local Stdio

Environment

Verification

Registry Identity

Official References

License

Installation

Use DeepSeek MCP with multiple AI models

Setup guide to use the local connector

Open the MCP settings

Run the connector command

Add DeepSeek as a server

Use it across models

Frequently asked questions

Related MCP Servers

Set up your own AI workspace now