Deepseek MCP Server

Model Context Protocol server for DeepSeek V4 API endpoints with stdio and Streamable HTTP transports.

Remote serverstreamable-http

What is the Deepseek MCP server?

If you already use Deepseek, the deepseek mcp server is the piece that lets your assistant work with it directly. Model Context Protocol server for DeepSeek V4 API endpoints with stdio and Streamable HTTP transports.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • chat_completion — DeepSeek V4 chat. Defaults to deepseek-v4-flash. Supports thinking: { "type": "enabled" | "disabled" }, reasoning_effort: "high" | "max", JSON
  • 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

Credentials and setup notes

Configuration is passed through the environment: DEEPSEEK_MCP_AUTH_TOKEN, REPLACE_WITH_TOKEN, DEEPSEEK_API_KEY, REPLACE_WITH_DEEPSEEK_KEY, DEEPSEEK_BASE_URL, MCP_HTTP_HOST, MCP_HTTP_PATH. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Installation

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

Where it fits

Among the knowledge and memory options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Deepseek's toolset — chat_completion, completion, list_models and 3 more — is a fair guide to whether it matches your workflow. It is maintained by DMontgomery40; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Worth knowing first

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
chat_completionDeepSeek 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.
completionDeepSeek V4 Pro FIM completion. Defaults to deepseek-v4-pro.
list_modelsReads the live DeepSeek model list.
get_user_balanceReads account balance and availability.
reset_conversationClears an in-memory conversation.
list_conversationsLists in-memory conversation IDs.

How to install the Deepseek MCP server

{
  "mcpServers": {
    "deepseek": {
      "command": "npx",
      "args": ["-y", "deepseek-mcp-server"],
      "env": {
        "DEEPSEEK_MCP_AUTH_TOKEN": "your-value",
        "REPLACE_WITH_TOKEN": "your-value",
        "DEEPSEEK_API_KEY": "your-value",
        "REPLACE_WITH_DEEPSEEK_KEY": "your-value",
        "DEEPSEEK_BASE_URL": "your-value",
        "MCP_HTTP_HOST": "your-value",
        "MCP_HTTP_PATH": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
DEEPSEEK_MCP_AUTH_TOKENCredential the server authenticates with.Yes
REPLACE_WITH_TOKENCredential the server authenticates with.Yes
DEEPSEEK_API_KEYCredential the server authenticates with.Yes
REPLACE_WITH_DEEPSEEK_KEYCredential the server authenticates with.Yes
DEEPSEEK_BASE_URLEndpoint or connection string the server talks to.Yes
MCP_HTTP_HOSTEndpoint or connection string the server talks to.Optional
MCP_HTTP_PATHFilesystem location the server is allowed to use.Optional

Example prompts to try

  • Use Deepseek to chat completion.
  • Use Deepseek to completion.
  • Use Deepseek to list models.

Frequently asked questions

It connects Deepseek to MCP-compatible AI assistants such as Claude and Cursor, exposing 6 tools (chat_completion, completion, list_models, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Deepseek directly.