DeepSeek MCP Server
io.github.DMontgomery40/deepseek·v0.3.1·352 starsOfficial DeepSeek MCP server for chat, completion, model listing, and balance endpoints.
352 stars
Reviews
Write oneNobody has reviewed DeepSeek MCP Server yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
DeepSeek MCP Server tools (6, 1 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
chat_completionCall DeepSeek POST /chat/completions with support for streaming, reasoning output, tool calls, and optional conversation persistence.
completionCall DeepSeek POST /completions for text/FIM completion workloads, including streaming support.
get_user_balanceCall DeepSeek GET /user/balance
list_conversationsList all currently stored conversation IDs
list_modelsCall DeepSeek GET /models
reset_conversationwrite actionDelete stored conversation history by conversation_id
Public scan report
scanner v0.1.10 · 2026-09-28 · same rubric, same numbers if you re-run it
- Code scan10 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 17 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How DeepSeek MCP Server compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 83/100
- higher than 68% of 4,464 AI and agents servers
- Tools
- 6
- the typical AI and agents server has 6
- Tools that change things
- 17%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 352
- more than 95% of 2,697 AI and agents servers
What its tools let an agent do: 5 read · 1 change
Install DeepSeek MCP Server in Claude Code, Cursor or VS Code
Runs npx -y deepseek-mcp-server on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add deepseek -- npx -y deepseek-mcp-server
What the publisher says
From the DeepSeek MCP Server repository's README, as published. We do not edit it. Read it on GitHub
DeepSeek MCP Server
An MCP server for DeepSeek's current V4.1 Flash API: text and visual chat, the Responses API, FIM completion, Files API lifecycle operations, model discovery, balance checks, and bounded in-memory conversations.
Version 1.0.1 uses the stable MCP TypeScript SDK v2 and serves both the 2026-07-28 protocol and stateless legacy clients.
What's current
As of September 10, 2026:
for deepseek-flash.
- The canonical fast model is deepseek-flash, currently DeepSeek V4.1 Flash.
- deepseek-v4-flash and deepseek-v4-flash-vision-exp are temporary aliases
September 14 until V4.1 Pro is released.
- DeepSeek announced that deepseek-v4-pro will begin serving V4.1 Flash on
inputs.
- V4.1 Flash accepts visual input through Chat Completions and Responses.
- The Files API supports upload, list, retrieve, and delete for reusable image
deepseek-flash.
- DeepSeek documents a 1M-token context window and up to 384K output tokens for
“Multimodal” here means image understanding. This server does not generate images, video, or audio.
Tools
The server exposes eleven tools:
function tools, JSON output, streaming aggregation, and optional conversation_id memory.
- chat_completion: text or visual Chat Completions, thinking controls,
controls, function/custom tools, web search, structured output, and semantic streaming aggregation.
- create_response: stateless Responses API calls with text/images, reasoning
reusable DeepSeek file_id.
- completion: FIM completion through /beta/completions.
- list_models: live model discovery.
- getuserbalance: account availability and balances.
- upload_file: upload base64 JPEG, PNG, GIF, or WebP data and receive a
- list_files: list uploaded files with cursor, order, and purpose filters.
- retrievefile: retrieve metadata for one fileid.
- delete_file: delete one uploaded file.
- reset_conversation: clear one local in-memory conversation.
- list_conversations: list local in-memory conversation IDs.
Every tool declares an MCP output schema and behavior annotations. Full provider payloads remain opt-in through includerawresponse=true.
Install
Node.js 20 or newer is required.
Run directly over stdio:
DEEPSEEK_API_KEY="REPLACE_WITH_DEEPSEEK_KEY" npx -y deepseek-mcp-server@1Codex CLI:
codex mcp add deepseek --env DEEPSEEK_API_KEY="REPLACE_WITH_DEEPSEEK_KEY" -- npx -y deepseek-mcp-server@1Claude Code:
claude mcp add deepseek --env DEEPSEEK_API_KEY="REPLACE_WITH_DEEPSEEK_KEY" -- npx -y deepseek-mcp-server@1Example MCP client configuration:
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
DeepSeek MCP Server: common questions
- Is DeepSeek MCP Server safe?
- Mostly: it is graded B (83/100). Read the DeepSeek MCP Server safety report
- How do I install DeepSeek MCP Server?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does DeepSeek MCP Server need an API key?
- Yes. The registry entry asks for
DEEPSEEK_API_KEY. - Is DeepSeek MCP Server maintained?
- The last commit was 52 days ago (2026-09-11). The latest release is v0.3.1.
- What can I use instead of DeepSeek MCP Server?
- Servers from other publishers that do the same job: three.ws Brain MCP server, Agent-Native Chat MCP server and DCC-MCP Core MCP server.
- How does DeepSeek MCP Server compare with other AI and agents MCP servers?
- safety score 83/100 (higher than 68% of 4,464 AI and agents servers); tools 6 (the typical AI and agents server has 6); tools that change things 17% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to DeepSeek MCP Server
Same job from other publishers: the closest match first, then the best rated.
- three.ws BrainList LLM providers and run chat completions through the three.ws multi-provider router.not reviewedEstablishedB
- Agent-Native ChatMinimal chat-first app with durable threads, actions, and the app-agent loopnot reviewedEstablishedA
- DCC-MCP CoreAgent control plane for DCC and engine hosts: one MCP endpoint, one tool contract.not reviewedEstablishedA
GeminiModel Context Protocol server for Google Gemini AI with chat, research, and groundingnot reviewedEstablishedA