Skip to main content
Glama
DeepSeek Subagent MCP Server

DeepSeek Subagent MCP Server

by kira4094

DeepSeek Subagent MCP Server

MCP server that lets Codex (or any MCP client) delegate sub-tasks to DeepSeek as a sub-agent. Single tool deepseek_task: give it a task (+ optional context), get back DeepSeek's final answer.

Features

  • 🧠 Single tool deepseek_task β€” delegate independent work (research/draft/review/refactor/analysis)

  • πŸ’° Defaults to deepseek-v4-flash (cost-effective), switch to deepseek-v4-pro via env

  • πŸ” Surfaces reasoning_content (V4 thinking mode) as a <thinking> block

  • ⚑ Zero non-MCP dependencies, one-line npx deploy

Related MCP server: deepseek-subagent-mcp

Requirements

Install & run

cd deepseek-subagent-mcp-server
npm install
npm start

Environment variables

Variable

Required

Default

Description

DEEPSEEK_API_KEY

βœ…

β€”

Your DeepSeek API key.

DEEPSEEK_MODEL

deepseek-v4-flash

Model. Also deepseek-v4-pro.

DEEPSEEK_BASE_URL

https://api.deepseek.com

Override endpoint (for proxies).

DEEPSEEK_MAX_TOKENS

8192

Default max output tokens.

Codex config

Add to Codex's MCP configuration:

{
  "mcpServers": {
    "deepseek-subagent": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "deepseek-subagent-mcp-server"],
      "env": {
        "DEEPSEEK_API_KEY": "your-deepseek-api-key",
        "DEEPSEEK_MODEL": "deepseek-v4-flash"
      }
    }
  }
}

Or run from a local checkout:

{
  "mcpServers": {
    "deepseek-subagent": {
      "command": "node",
      "args": ["D:\\GitHub\\MCP\\deepseek-subagent-mcp-server\\src\\index.js"],
      "env": {
        "DEEPSEEK_API_KEY": "your-key-here"
      }
    }
  }
}

Tool: deepseek_task

Parameter

Type

Required

Description

task

string

βœ…

The sub-task for DeepSeek. Be specific about what to do and output format.

context

string

Optional context material (code, notes, snippets).

system

string

Optional custom system prompt (defaults to a subagent persona).

max_tokens

number

Max output tokens. Default 8192.

temperature

number

0-2. Omit to use model default.

Example usage

# Delegate a code review
deepseek_task(task="Review this function for bugs and edge cases", context="<code>...")

# Delegate a research task
deepseek_task(task="Summarize the key risks of a subscription pricing model")

License

MIT

Available Tools

1 tool
deepseek_taskA

Delegate a sub-task to DeepSeek as a sub-agent and get back its result. Use this for work that can be done independently: research, drafting, code review, refactoring, analysis, writing, or any self-contained task that shouldn't pollute the main conversation. The caller (Codex) supplies a task description and optional context; DeepSeek completes the task in one shot and returns the final answer (with reasoning, if produced). Default model: deepseek-v4-flash. Override via DEEPSEEK_MODEL env (e.g. DeepSeek-V4-Pro-0813).

Inputs: task (required), system, context, max_tokens, +2 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 1 tool

    Disambiguation5/5

    There is only one tool, so there is no possibility of confusion or overlapping purposes. The tool clearly covers the single action of delegating a sub-task to DeepSeek.

    Naming Consistency5/5

    With a single tool, there is no pattern to be inconsistent about. The name 'deepseek_task' is descriptive and follows a clear noun-based naming convention.

    Tool Count3/5

    One tool is on the thin side; while the server's purpose is narrow, a richer integration might include multiple tools (e.g., different task types or configuration options). The count is borderline but not unreasonable for a single-purpose sub-agent server.

    Completeness4/5

    The tool fully covers the stated purpose of delegating a self-contained task and returning the result. Minor gaps exist, such as no way to manage task history or configure multiple output modes, but these are not essential to the core workflow.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      Enables using DeepSeek models as a small, cheap supervised worker from any MCP-compatible client, providing fast flash and deep reasoning tools for bounded tasks.
      2
      56
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Enables AI coding agents like Claude Code or Codex to delegate tasks to a DeepSeek Harness subagent with its own context window, providing tools for task delegation, result waiting, continuation, and supervision with sandboxed execution.
      6
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables MCP clients like Codex and DSH to invoke DeepSeek subagents for inspect, plan, review, and implement tasks, with write protection, rollback, and status reporting.
      215 npm
      MIT