DeepSeek MCP Server
Wire DeepSeek chat, completions, model discovery, and balance checks into your agent stack through a single official MCP server.
Overview
DeepSeek MCP Server is a MCP server for the Build phase that exposes official DeepSeek chat, completion, model listing, and balance APIs to MCP clients.
What is this MCP server?
- Official DeepSeek MCP for chat and completion endpoints
- Model listing tools to pick the right DeepSeek model in-agent
- Balance endpoint exposure for spend and quota awareness
- stdio npm transport via deepseek-mcp-server 0.3.1
- Single required secret: DEEPSEEK_API_KEY for upstream requests
- Server version 0.3.1
- npm identifier deepseek-mcp-server
- Capabilities: chat, completion, model listing, balance endpoints
Community signal: 340 GitHub stars.
What problem does it solve?
Calling DeepSeek from an agent usually means scattering fetch snippets and env wiring instead of a consistent MCP tool surface.
Who is it for?
Solo builders standardizing DeepSeek inside Claude Code, Cursor, or Codex during agent and backend experiments.
Skip if: Teams that only use Anthropic or OpenAI exclusively with no DeepSeek account.
What do I get? / Deliverables
Install one MCP server so your agent can chat, complete, list models, and check balance on DeepSeek with a single API key.
- MCP tools for DeepSeek chat and completion calls
- In-agent DeepSeek model catalog queries
- Balance visibility for API usage monitoring during development
Recommended MCP Servers
Journey fit
DeepSeek access belongs in Build when you are assembling agents, backends, or scripts that call an LLM provider. Agent-tooling is the natural shelf for an official provider MCP that replaces ad-hoc API wrappers in Claude Code or Cursor.
How it compares
Official DeepSeek API MCP adapter, not a prompt library or RAG skill.
Common Questions / FAQ
Who is io.github.DMontgomery40/deepseek for?
Developers and indie builders who use DeepSeek as an LLM provider and want MCP-native chat, completion, model list, and balance tools in their agent IDE.
When should I use io.github.DMontgomery40/deepseek?
Use it in Build while wiring agents or scripts that must call DeepSeek, or when you need in-session model and balance visibility.
How do I add io.github.DMontgomery40/deepseek to my agent?
Install deepseek-mcp-server from npm, set DEEPSEEK_API_KEY, and register the stdio MCP server in Claude Code, Cursor, or another MCP-compatible client.