DeepSeek Subagent MCP Server
DeepSeek Subagent MCP Server
MCP-Server, der es Codex (oder jedem MCP-Client) ermöglicht, Teilaufgaben an DeepSeek als Sub-Agenten zu delegieren.
Ein einziges Tool deepseek_task: Übergib eine Aufgabe (+ optionalen Kontext) und erhalte die endgültige Antwort von DeepSeek.
Funktionen
🧠 Ein einziges Tool
deepseek_task— delegiere unabhängige Aufgaben (Recherche, Entwurf, Review, Refactoring, Analyse)💰 Standardmäßig deepseek-v4-flash (kostengünstig), umschaltbar auf
deepseek-v4-proper Umgebungsvariable🔍 Zeigt
reasoning_content(V4-Denkmodus) als<thinking>-Block an⚡ Keine Abhängigkeiten außer MCP, Ein-Zeilen-Deployment per
npx
Related MCP server: deepseek-mcp
Voraussetzungen
Node.js >= 18
Ein DeepSeek-API-Schlüssel: https://platform.deepseek.com
Installation und Ausführung
cd deepseek-subagent-mcp-server
npm install
npm startUmgebungsvariablen
Variable | Erforderlich | Standard | Beschreibung |
| ✅ | — | Ihr DeepSeek-API-Schlüssel. |
|
| Modell. Auch | |
|
| Endpunkt überschreiben (für Proxys). | |
|
| Standardwert für maximale Ausgabetokens. |
Codex-Konfiguration
Füge das zur MCP-Konfiguration von Codex hinzu:
{
"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"
}
}
}
}Oder führe es aus einem lokalen Checkout aus:
{
"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 | Typ | Erforderlich | Beschreibung |
| string | ✅ | Die Teilaufgabe für DeepSeek. Beschreibe genau, was zu tun ist und welches Ausgabeformat erwartet wird. |
| string | Optionaler Kontext (Code, Notizen, Snippets). | |
| string | Optionaler eigener System-Prompt (Standard: Persona eines Sub-Agenten). | |
| number | Maximale Ausgabetokens. Standard: 8192. | |
| number | 0-2. Weglassen, um den Modellstandard zu verwenden. |
Beispielverwendung
# 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")Verwandte Projekte
Lizenz
MIT
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Tools
Related MCP Servers
- AlicenseDqualityDmaintenanceAllows seamless integration of DeepSeek's language models with MCP-compatible applications like Claude Desktop, supporting features such as model selection, temperature control, and multi-turn conversations with automatic model fallback.22,1982MIT
- AlicenseAqualityDmaintenanceEnables using DeepSeek models as a small, cheap supervised worker from any MCP-compatible client, providing fast flash and deep reasoning tools for bounded tasks.253MIT
- AlicenseNot gradedqualityBmaintenanceConnects MCP clients to DeepSeek API, including DeepSeek-R1 reasoning with visible chain-of-thought. Provides four tools: generate, chat, reason, and list models.1MIT
- AlicenseNot gradedqualityBmaintenanceEnables dispatching work to DeepSeek Harness agents from Claude Code/Codex, with native progress UI, tier policy, and vision/image generation through MCP tools.0101MIT
Related MCP Connectors
A paid remote MCP for OpenAI Codex agent coordination MCP, built to return verdicts, receipts, usage
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Free public MCP for AI agents — 193 tools, 44 workflows. No API key.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/kira4094/deepseek-subagent-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server