DeepSeek Subagent MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@DeepSeek Subagent MCP Server Review this code for bugs and edge cases"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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
π§ Single tool
deepseek_taskβ delegate independent work (research/draft/review/refactor/analysis)π° Defaults to deepseek-v4-flash (cost-effective), switch to
deepseek-v4-provia envπ Surfaces
reasoning_content(V4 thinking mode) as a<thinking>blockβ‘ Zero non-MCP dependencies, one-line
npxdeploy
Related MCP server: deepseek-subagent-mcp
Requirements
Node.js >= 18
A DeepSeek API key: https://platform.deepseek.com
Install & run
cd deepseek-subagent-mcp-server
npm install
npm startEnvironment variables
Variable | Required | Default | Description |
| β | β | Your DeepSeek API key. |
|
| Model. Also | |
|
| Override endpoint (for proxies). | |
|
| 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 |
| string | β | The sub-task for DeepSeek. Be specific about what to do and output format. |
| string | Optional context material (code, notes, snippets). | |
| string | Optional custom system prompt (defaults to a subagent persona). | |
| number | Max output tokens. Default 8192. | |
| 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")Related projects
License
MIT
Available Tools
1 tooldeepseek_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 changelogβ¦
TDQS
Scored across 1 tool
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.
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.
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.
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
Task management your AI agents can actually run. One line becomes a context-ready task over MCP.
Discover and call AI agents via MCP. Supports A2A agents and platform agents with async tasks.
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables using DeepSeek models as a small, cheap supervised worker from any MCP-compatible client, providing fast flash and deep reasoning tools for bounded tasks.256MIT
- AlicenseAqualityCmaintenanceEnables 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.6MIT
- AlicenseNot gradedqualityBmaintenanceExposes DeepSeek as a callable MCP tool, enabling ChatGPT connectors and other MCP clients to invoke it for cross-vendor independent review tasks.7 npm5MIT
- AlicenseNot gradedqualityCmaintenanceEnables 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 npmMIT