Log inSubmit server
Deepseek MCP Server logo

Deepseek MCP Server

by arikusi

Connects MCP clients to DeepSeek for chat, reasoning, sessions, function calling, JSON output, and fill-in-the-middle completion.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Deepseek MCP Server

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "arikusi-deepseek-mcp-server": {
      "command": "npx",
      "args": [
        "@arikusi/deepseek-mcp-server"
      ],
      "env": {
        "DEEPSEEK_API_KEY": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

arikusi/deepseek-mcp-server exposes DeepSeek models to MCP clients through chat, fill-in-the-middle, and session-management tools. It supports deepseek-flash and deepseek-v4-pro, multi-turn context, optional thinking mode, function calling, streaming, JSON responses, and cost tracking. Use the hosted Streamable HTTP endpoint for a no-install setup, or run the package locally over stdio with a DeepSeek API key. The server also provides MCP resources for model information, configuration, and usage statistics.

Use cases

  • Ask DeepSeek to explain technical concepts
  • Generate code between a prefix and suffix
  • Maintain multi-turn reasoning sessions
  • Call external tools through function definitions
  • Produce schema-validated JSON responses

Key features

  • DeepSeek Flash and V4 Pro model access
  • Multi-turn conversation sessions
  • Thinking mode and reasoning effort controls
  • Function calling with up to 128 tools
  • Fill-in-the-middle completion
  • Cache-aware cost tracking

Tools3

What Deepseek MCP Server lets your agent do. Expand a tool for its parameters.

Self-reported~115 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

20/20 checks healthy over the last 79d

Supply-chain signal

1 high-severity advisory on record for this package. Most advisories affect transitive dependencies and may not be exploitable in this server's actual usage — this is a directional signal, not a security audit.

Critical 0High 1Medium 1Low 0

Scanned 9d ago via OSV.dev · @arikusi/deepseek-mcp-server (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars26Stargazers on the source repository.
npm downloads2.1kPackage downloads in the last 30 days.
Last commit2d agoMost recent push to the default branch.
Tools exposed3Callable tools this server registers over MCP.
Directory activity13 viewsConfig copies, upvotes, and views on AllMCPs.

How Deepseek MCP Server works

What arikusi/deepseek-mcp-server does

arikusi/deepseek-mcp-server connects MCP-compatible clients to DeepSeek's API. Its primary chat interface supports the current deepseek-flash model and deepseek-v4-pro, with both models offering a 1M-token context window and optional thinking mode. Older model names such as deepseek-chat, deepseek-reasoner, and deepseek-v4-flash remain accepted and are mapped to the current flash model behavior.

The server is aimed at conversational AI, reasoning tasks, structured generation, and coding workflows. It tracks request costs while accounting for cache hits and misses and the peak or off-peak rate that applied to each request.

How it works

MCP clients call the server's tools rather than contacting DeepSeek directly. The deepseek_chat tool accepts conversation messages and options such as model selection, token limits, temperature, streaming, thinking, JSON mode, response schemas, and function-calling definitions. Thinking can be enabled or disabled per request, and reasoning effort can be selected while thinking is active.

Conversation state can be retained with a session_id, allowing multi-turn interactions across requests. Model fallback and circuit-breaker behavior help manage model or service failures. Three MCP resources are also exposed: deepseek://models, deepseek://config, and deepseek://usage.

Setup and configuration

A DeepSeek API key and Node.js 22 or newer are required for a local installation. Install the published package globally with npm, or clone the repository, install dependencies, and build the TypeScript project. Configure the local stdio server with the DEEPSEEK_API_KEY environment variable through the MCP client's server settings.

A hosted endpoint is available at https://deepseek-mcp.tahirl.com/mcp. Clients that support HTTP transport can use it without installing Node.js; requests still use your own DeepSeek API key through an Authorization header. The server can also be self-hosted with Streamable HTTP by setting its transport to HTTP. Docker deployment is supported through the included container configuration and health checks.

Tools and capabilities

  • deepseek_chat: Sends chat messages to DeepSeek, with function calling for up to 128 tool definitions, streaming, thinking mode, JSON output, schema validation, and automatic cost tracking.
  • deepseek_fim: Generates text between a supplied prefix and optional suffix. It targets code completion and content infilling rather than conversational exchanges and uses DeepSeek's Beta endpoint in non-thinking mode.
  • deepseek_sessions: Lists, deletes, and clears stored conversation sessions.

The server includes 12 prompt templates covering tasks such as debugging, code review, and function calling. Multimodal content parts for text and images are available when multimodal support is enabled with ENABLE_MULTIMODAL=true.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Deepseek MCP Server

arikusi/deepseek-mcp-server is an MCP server that connects MCP clients to DeepSeek models through chat, fill-in-the-middle completion, and session-management tools. It supports thinking mode, function calling, JSON output, streaming, multi-turn sessions, and cost tracking, with local stdio and hosted HTTP deployment options.

Install it locally with Node.js 22 or newer using `npm install -g @arikusi/deepseek-mcp-server`, then configure `DEEPSEEK_API_KEY` in your MCP client. You can also clone the repository, run `npm install`, and build it, or use the hosted HTTP endpoint without a local installation.

Connect Cursor using the hosted endpoint `https://deepseek-mcp.tahirl.com/mcp` and provide an Authorization header containing your DeepSeek API key. Cursor can also use a local stdio configuration that launches the npm package with `DEEPSEEK_API_KEY`.

Yes. The `deepseek_chat` tool accepts OpenAI-compatible function definitions and supports up to 128 tool definitions, along with tool-choice settings such as automatic, none, required, or a selected function.

Related MCP servers

All in Aggregators All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewDeepseek MCP Server AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/arikusi-deepseek-mcp-server?style=directory)](https://allmcps.com/mcp/arikusi-deepseek-mcp-server)
HTML Embed
<a href="https://allmcps.com/mcp/arikusi-deepseek-mcp-server"><img src="https://allmcps.com/api/badge/arikusi-deepseek-mcp-server?style=directory" alt="Deepseek MCP Server on AllMCPs" /></a>