The DeepSeek MCP Server provides integration with DeepSeek's API, exposing tools for chat completions, model information retrieval, and account balance checking through the Model Context Protocol. It supports both remote hosted endpoints and local deployment options, with authentication via bearer tokens, enabling AI assistants like Claude, Cursor, and Codex to interact with DeepSeek's language models. The server solves the problem of connecting MCP-compatible applications to DeepSeek's services without direct API management.
Public tool metadata for what this MCP can expose to an agent.
deepseek_chatChat with DeepSeek AI models (Chat + Reasoner). Supports function calling, thinking mode, JSON output, cost tracking.9 paramsChat with DeepSeek AI models (Chat + Reasoner). Supports function calling, thinking mode, JSON output, cost tracking.
modelstringdeepseek-chat · deepseek-reasonerdefault: deepseek-chattoolsarraystreambooleanmessagesarraythinkingobjectjson_modebooleanmax_tokensnumbertemperaturenumbertool_choicevalueModel Context Protocol server for the current DeepSeek V4 API.
As of April 24, 2026, DeepSeek's public API reference documents:
POST /chat/completions with deepseek-v4-flash and deepseek-v4-proPOST /beta/completions for V4 Pro FIM completionGET /modelsGET /user/balanceThis server exposes only those documented API surfaces. It does not ship a V4 monitor, speculative image/video/upload tools, or automatic model substitution.
chat_completion: DeepSeek 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.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.https://deepseek-mcp.ragweld.com/mcpAuthorization: Bearer <token>Codex CLI:
export DEEPSEEK_MCP_AUTH_TOKEN="REPLACE_WITH_TOKEN"
codex mcp add deepseek --url https://deepseek-mcp.ragweld.com/mcp --bearer-token-env-var DEEPSEEK_MCP_AUTH_TOKEN
Claude Code:
export DEEPSEEK_MCP_AUTH_TOKEN="REPLACE_WITH_TOKEN"
claude mcp add --transport http deepseek https://deepseek-mcp.ragweld.com/mcp --header "Authorization: Bearer $DEEPSEEK_MCP_AUTH_TOKEN"
Cursor:
node -e 'const fs=require("fs"),p=process.env.HOME+"/.cursor/mcp.json";let j={mcpServers:{}};try{j=JSON.parse(fs.readFileSync(p,"utf8"))}catch{};j.mcpServers={...(j.mcpServers||{}),deepseek:{url:"https://deepseek-mcp.ragweld.com/mcp",headers:{Authorization:"Bearer ${env:DEEPSEEK_MCP_AUTH_TOKEN}"}}};fs.mkdirSync(process.env.HOME+"/.cursor",{recursive:true});fs.writeFileSync(p,JSON.stringify(j,null,2));'
DEEPSEEK_API_KEY="REPLACE_WITH_DEEPSEEK_KEY" npx -y deepseek-mcp-server
Docker:
docker pull docker.io/dmontgomery40/deepseek-mcp-server:0.5.0
docker run --rm -i -e DEEPSEEK_API_KEY="REPLACE_WITH_DEEPSEEK_KEY" docker.io/dmontgomery40/deepseek-mcp-server:0.5.0
Required:
DEEPSEEK_API_KEY=your-api-key
Optional:
DEEPSEEK_BASE_URL=https://api.deepseek.com
DEEPSEEK_REQUEST_TIMEOUT_MS=120000
DEEPSEEK_DEFAULT_MODEL=deepseek-v4-flash
MCP_TRANSPORT=stdio
MCP_HTTP_HOST=127.0.0.1
MCP_HTTP_PORT=3001
MCP_HTTP_PATH=/mcp
MCP_HTTP_STATEFUL_SESSION=false
CONVERSATION_MAX_MESSAGES=200
npm run build
npm test
DEEPSEEK_API_KEY="REPLACE_WITH_DEEPSEEK_KEY" npm run test:live
DEEPSEEK_MCP_AUTH_TOKEN="REPLACE_WITH_TOKEN" npm run test:remote
The live smoke test performs real DeepSeek requests for model listing, balance, non-thinking chat, thinking streaming chat with reasoning_content, FIM completion, and MCP tool calls.
io.github.DMontgomery40/deepseekdeepseek-mcp-serverdocker.io/dmontgomery40/deepseek-mcp-server:0.5.0MIT
DEEPSEEK_API_KEY*secretDeepSeek API key used for upstream DeepSeek requests
io.github.mindstone/mcp-server-microsoft-teams
com.mintmcp/outlook-email
helbertparanhos/resend-email-mcp
marlinjai/email-mcp
io.github.mindstone/mcp-server-email-imap
io.github.osamahassouna/email-playbook-mcp