🧠DeepSeek MCP Server
About
MCP server that enhances Claude's reasoning capabilities by integrating DeepSeek R1's advanced reasoning engine
Details
- License
- MIT
Explore
- Integrates DeepSeek R1’s advanced reasoning engine.
- Enhances Claude’s reasoning capabilities.
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
—
chat_completion
Primary DeepSeek V4 chat tool for single-turn and multi-turn generation. Defaults to `deepseek-v4-flash`; use `deepseek-v4-pro` for higher-capability reasoning. Provide either `message` (simple single user turn) or `messages` (full chat history); if both are provided, `messages` is used. Thinking mode is enabled by DeepSeek by default; pass `thinking:{type:"disabled"}` for non-thinking mode, and use `reasoning_effort:"low"|"high"|"max"` when thinking is enabled. Use `conversation_id` to persist context across calls and `clear_conversation=true` to reset stored state before sending the next turn. Set `include_raw_response=true` only for debugging because it returns the full provider payload.
completion
DeepSeek V4 Pro FIM completion tool for prompt/suffix fill-in-the-middle workflows. Defaults to `deepseek-v4-pro`. Use this when you need raw completion text instead of chat message formatting. Set `include_raw_response=true` only when you need the full provider payload for debugging.
create_response
Create a stateless DeepSeek V4 response using the native OpenAI-compatible Responses API. Defaults to `deepseek-v4-flash`. Provide `input`, `instructions`, or both. Use `reasoning.effort` for thinking control, `tools` for function or server-side web-search tools, and `stream=true` for semantic SSE aggregation. This tool does not persist provider-side response state; send the full input history for multi-turn work. Set `include_raw_response=true` only for debugging because it returns the full provider payload.
list_models
List available DeepSeek models for model selection and validation. This tool takes no parameters. Use it before passing an explicit model ID to generation tools.
get_user_balance
Return the current DeepSeek account balance and availability status. This tool takes no parameters and is read-only. Use it for account health checks when diagnosing provider-side failures.
reset_conversation
Delete stored in-memory chat history for a `conversation_id`. Use this when you want to keep the same ID but start a fresh thread. This only affects server-side memory in the current MCP process.
list_conversations
List all conversation IDs currently stored in this MCP process memory. This tool takes no parameters and does not call the DeepSeek API. Useful for debugging conversation persistence behavior.
- chat_completion: Primary DeepSeek V4 chat tool for single-turn and multi-turn generation. Defaults to deepseek-v4-flash; use deepseek-v4-pro for higher-capability reasoning. Provide either message (simple single user turn) or messages (full chat history); if both are provided, messages is used. Thinking mode is enabled by DeepSeek by default; pass thinking:{type:"disabled"} for non-thinking mode, and use reasoning_effort:"low"|"high"|"max" when thinking is enabled. Use conversation_id to persist context across calls and clear_conversation=true to reset stored state before sending the next turn. Set include_raw_response=true only for debugging because it returns the full provider payload.
- completion: DeepSeek V4 Pro FIM completion tool for prompt/suffix fill-in-the-middle workflows. Defaults to deepseek-v4-pro. Use this when you need raw completion text instead of chat message formatting. Set include_raw_response=true only when you need the full provider payload for debugging.
- create_response: Create a stateless DeepSeek V4 response using the native OpenAI-compatible Responses API. Defaults to deepseek-v4-flash. Provide input, instructions, or both. Use reasoning.effort for thinking control, tools for function or server-side web-search tools, and stream=true for semantic SSE aggregation. This tool does not persist provider-side response state; send the full input history for multi-turn work. Set include_raw_response=true only for debugging because it returns the full provider payload.
- list_models: List available DeepSeek models for model selection and validation. This tool takes no parameters. Use it before passing an explicit model ID to generation tools.
- get_user_balance: Return the current DeepSeek account balance and availability status. This tool takes no parameters and is read-only. Use it for account health checks when diagnosing provider-side failures.
- reset_conversation: Delete stored in-memory chat history for a conversation_id. Use this when you want to keep the same ID but start a fresh thread. This only affects server-side memory in the current MCP process.
- list_conversations: List all conversation IDs currently stored in this MCP process memory. This tool takes no parameters and does not call the DeepSeek API. Useful for debugging conversation persistence behavior.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"\ud83e\udde0 deepseek mcp server": {
"deepseek-MCP-server": {
"command": "uv",
"args": [
"venv"
]
}
}
}
}McpServers
{
"deepseek-MCP-server": {
"command": "uv",
"args": [
"venv"
]
}
}MCP server that enhances Claude's reasoning capabilities by integrating DeepSeek R1's advanced reasoning engine
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
