Deepseek Mcp Server
About
MCP server for DeepSeek V4 (v4-flash, v4-pro, 1M context): chat, reasoning, function calling, thinking mode, cost tracking. deepseek-chat/reasoner aliases supported.
Details
- Author
- arikusi
- GitHub stars
- 17
- Downloads
- 294
- Categories
- Other
Jump to
- DeepSeek V4 models with 1M context and thinking mode
- Multi-turn sessions with automatic context preservation
- Function calling with up to 128 tool definitions
- Cache-aware cost tracking with cache hit/miss breakdown
- MCP resources for model info, config, and usage
- JSON output mode with schema validation and repair
- Fill-in-the-Middle (FIM) for code/content completion
- Session management (list, delete, clear sessions)
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 Mcp ServerCommand (node, npx, python, etc.)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
From the repository
Install it via npx or npm install -g @arikusi/deepseek-mcp-server, then add it to your MCP client using either stdio transport (local) or the hosted HTTP endpoint at https://deepseek-mcp.tahirl.com/mcp (remote, no install required). You need a DeepSeek API key from https://platform.deepseek.com. Use commands like claude mcp add or manual configuration in JSON.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"deepseek mcp server": {
"deepseek-mcp-server-arikusi": {
"command": "node",
"args": [
"dist/index.js"
],
"env": {
"TRANSPORT": "http",
"HTTP_PORT": "3000",
"DEEPSEEK_API_KEY": "your-key"
}
}
}
}
}
McpServers
{
"deepseek-mcp-server-arikusi": {
"command": "node",
"args": [
"dist/index.js"
],
"env": {
"TRANSPORT": "http",
"HTTP_PORT": "3000",
"DEEPSEEK_API_KEY": "your-key"
}
}
}
<p align="center">
![]()
</p>
<h1 align="center">DeepSeek MCP Server</h1>
<p align="center">
MCP server for DeepSeek V4 (v4-flash and v4-pro, 1M context) with multi-turn sessions, function calling, thinking mode, and cost tracking.
</p>
<p align="center">
<a href="https://www.npmjs.com/package/@arikusi/deepseek-mcp-server"></a>
<a href="https://www.npmjs.com/package/@arikusi/deepseek-mcp-server"></a>
<a href="https://opensource.org/licenses/MIT"></a>
<a href="https://nodejs.org/"></a>
<a href="https://www.typescriptlang.org/"></a>
<a href="https://api-docs.deepseek.com"></a>
<a href="https://github.com/arikusi/deepseek-mcp-server/actions"></a>
</p>
<p align="center">
Compatible with Claude Code, Gemini CLI, Cursor, Windsurf, and any MCP-compatible client.<br />
Officially listed on the <a href="https://registry.modelcontextprotocol.io/?q=io.github.arikusi"><strong>MCP Registry</strong></a>, <a href="https://smithery.ai/servers/arikusi/deepseek-mcp-server">Smithery</a>, <a href="https://glama.ai/mcp/servers/arikusi/deepseek-mcp-server">Glama</a>, <a href="https://lobehub.com/mcp/arikusi-deepseek-mcp-server">LobeHub</a>, and <a href="https://fronteir.ai/mcp/arikusi-deepseek-mcp-server">Fronteir AI</a>.
</p>
<p align="center">
<a href="https://registry.modelcontextprotocol.io/?q=io.github.arikusi"></a>
<a href="https://smithery.ai/servers/arikusi/deepseek-mcp-server"></a>
<a href="https://lobehub.com/mcp/arikusi-deepseek-mcp-server"></a>
</p>
<p align="center">
<a href="https://glama.ai/mcp/servers/arikusi/deepseek-mcp-server">
</a>
</p>
> v2.0.0 runs on DeepSeek V4. Two models, deepseek-v4-flash (fast and economical) and deepseek-v4-pro (top capability), both with a 1M-token context window and optional chain-of-thought thinking. Existing deepseek-chat and deepseek-reasoner setups keep working as aliases, so upgrading is drop-in.
Quick Start
Remote (No Install)
Use the hosted endpoint directly — no npm install, no Node.js required. Bring your own DeepSeek API key:
Claude Code:
claude mcp add --transport http deepseek \
https://deepseek-mcp.tahirl.com/mcp \
--header "Authorization: Bearer YOUR_DEEPSEEK_API_KEY"
Cursor / Windsurf / VS Code:
{
"mcpServers": {
"deepseek": {
"url": "https://deepseek-mcp.tahirl.com/mcp",
"headers": {
"Authorization": "Bearer ${DEEPSEEK_API_KEY}"
}
}
}
}
Local (stdio)
Claude Code:
claude mcp add -s user deepseek npx @arikusi/deepseek-mcp-server -e DEEPSEEK_API_KEY=your-key-here
Gemini CLI:
gemini mcp add deepseek npx @arikusi/deepseek-mcp-server -e DEEPSEEK_API_KEY=your-key-here
Scope options (Claude Code):
- -s user: Available in all your projects (recommended)
- -s local: Only in current project (default)
- -s project: Project-specific .mcp.json file
Get your API key: https://platform.deepseek.com
---
Features
- DeepSeek V4: deepseek-v4-flash and deepseek-v4-pro, both with 1M context and optional chain-of-thought thinking mode
- Multi-Turn Sessions: Conversation context preserved across requests via session_id parameter
- Model Fallback & Circuit Breaker: Automatic fallback between models with circuit breaker protection against cascading failures
- MCP Resources: deepseek://models, deepseek://config, deepseek://usage — query model info, config, and usage stats
- Thinking Mode: Enable thinking on deepseek-chat with thinking: {type: "enabled"}
- JSON Output Mode: Structured JSON responses with json_mode: true
- Schema-Validated JSON: Pass a response_schema and the server validates the output against it, with bounded repair retries and a ReDoS guard on schema patterns
- Function Calling: OpenAI-compatible tool use with up to 128 tool definitions
- Fill-in-the-Middle (FIM): Code and content completion between a prefix and suffix via the deepseek_fim tool
- Cache-Aware Cost Tracking: Automatic cost calculation with cache hit/miss breakdown
- Session Management Tool: List, delete, and clear sessions via deepseek_sessions tool
- Configurable: Environment-based configuration with validation
- 12 Prompt Templates: Templates for debugging, code review, function calling, and more
- Streaming Support: Real-time response generation
- Multimodal Ready: Content part types for text + image input (enable with ENABLE_MULTIMODAL=true)
- Remote Endpoint: Hosted at deepseek-mcp.tahirl.com/mcp — BYOK (Bring Your Own Key), no install needed
- HTTP Transport: Self-hosted remote access via Streamable HTTP with TRANSPORT=http
- Docker Ready: Multi-stage Dockerfile with health checks for containerized deployment
- Tested: 280 tests, ~89% line coverage
- Type-Safe: Full TypeScript implementation
- MCP Compatible: Works with any MCP-compatible CLI (Claude Code, Gemini CLI, etc.)
Installation
Prerequisites
- Node.js 20+
- A DeepSeek API key (get one at https://platform.deepseek.com)
Manual Installation
If you prefer to install manually:
npm install -g @arikusi/deepseek-mcp-server
From Source
1. Clone the repository
git clone https://github.com/arikusi/deepseek-mcp-server.git
cd deepseek-mcp-server
2. Install dependencies
npm install
3. Build the project
npm run build
Usage
Once configured, your MCP client will have access to deepseek_chat, deepseek_fim, and deepseek_sessions tools, plus 3 MCP resources.
Example prompts:
"Use DeepSeek to explain quantum computing"
"Ask DeepSeek Reasoner to solve: If I have 10 apples and buy 5 more..."
Your MCP client will automatically call the deepseek_chat tool.
Manual Configuration (Advanced)
If your MCP client doesn't support the add command, manually add to your config file:
{
"mcpServers": {
"deepseek": {
"command": "npx",
"args": ["@arikusi/deepseek-mcp-server"],
"env": {
"DEEPSEEK_API_KEY": "your-api-key-here"
}
}
}
}
Config file locations:
- Claude Code: ~/.claude.json (add to projects["your-project-path"].mcpServers section)
- Other MCP clients: Check your client's documentation for config file location
Available Tools
deepseek_chat
Chat with DeepSeek AI models with automatic cost tracking and function calling support.
Parameters:
…
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.



