Log inSubmit server
DeepSeek MCP Server logo

DeepSeek MCP Server

Connect MCP clients to DeepSeek for chat, reasoning, visual input, completions, files, models, balances, and local conversation state.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install DeepSeek MCP Server

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "deepseek-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "deepseek-mcp-server"
      ],
      "env": {
        "DEEPSEEK_API_KEY": "YOUR_VALUE_HERE",
        "DEEPSEEK_REQUEST_TIMEOUT_MS": "YOUR_VALUE_HERE",
        "MCP_TOOL_RATE_LIMIT": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Automated check passed— started and listed 11 tools correctly (Today).

Overview

DeepSeek MCP Server exposes DeepSeek chat, Responses, FIM completion, model discovery, balance, Files API, and local conversation tools through MCP. It runs over stdio with Node.js 20+ and authenticates using a DeepSeek API key. Reach for it when an MCP client needs text or image understanding, reasoning controls, reusable image files, or live account and model information. Responses calls remain stateless, while chat can use bounded in-memory conversation IDs.

Use cases

  • Build an MCP-powered DeepSeek chat assistant
  • Analyze images from URLs, base64 data, or uploaded files
  • Discover available DeepSeek models and capabilities
  • Run fill-in-the-middle code completion
  • Check balances and manage reusable image files

Key features

  • Text and visual chat completions
  • Stateless Responses API with reasoning controls
  • Fill-in-the-middle completion
  • Live model and account balance discovery
  • DeepSeek image file lifecycle management
  • Optional in-memory conversation tracking

Tools11

What DeepSeek MCP Server lets your agent do. Expand a tool for its parameters.

Verified live~3.9k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

30/30 checks healthy over the last 92d

What it can do

From the 11 tools this server returned when we ran it; 11 declare their own safety hints.

Can delete or modify data · 2Writes files · 1Makes network requests · 9Read-only tools · 8
Network at startup3 connections
Files written at startupNone
Install scriptsNone
npm provenanceNot published
Package age657 days
Maintainers1

Observed 2026-11-10 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 7d ago via OSV.dev · deepseek-mcp-server (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars364Stargazers on the source repository.
npm downloads2.2kPackage downloads in the last 30 days.
Last commit11d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed11Callable tools this server registers over MCP.
Directory activity11 viewsConfig copies, upvotes, and views on AllMCPs.

How DeepSeek MCP Server works

What DeepSeek MCP Server does

DeepSeek MCP Server connects MCP clients to DeepSeek V4.1 Flash and V4 Pro APIs. It covers conversational generation, visual image understanding, Responses API requests, fill-in-the-middle completion, model discovery, account balance checks, and image file management.

The conversational tools support text and image inputs, reasoning controls, structured output, function tools, and aggregated streaming results. chat_completion can optionally associate requests with a local in-memory conversation_id. create_response instead expects the caller to provide the full input history for each stateless request.

Image understanding is available through image URLs, supported base64 data URLs, or reusable file IDs. The service does not generate images, video, or audio.

How it works

The package communicates with an MCP client over stdio. Requests are sent to DeepSeek using the configured API key, and streamed provider responses are aggregated into one MCP result rather than forwarded as partial MCP notifications. Each tool declares an MCP output schema and behavior annotations; full provider payloads can be requested with include_raw_response=true.

list_models reports live account availability and model details such as display names, context and output limits, modalities, effort levels, and API capabilities. deepseek-flash supports visual input through Chat Completions and Responses, while deepseek-v4-pro accepts text input and can run web_search inside create_response. DeepSeek ignores web_search when the selected model is Flash.

The Responses integration supports the custom apply_patch tool. When DeepSeek returns a custom tool call, the client must execute it and send the resulting custom_tool_call_output as part of later history. Other built-in Responses tool types, including file_search, code_interpreter, and mcp, are ignored.

Setup and configuration

Node.js 20 or newer is required. Launch the server with npx and provide DEEPSEEK_API_KEY:

bash
DEEPSEEK_API_KEY="your-deepseek-key" npx -y deepseek-mcp-server

A typical stdio client configuration uses npx as the command, passes the package as an argument, and places the API key in the client’s environment configuration. Codex CLI and Claude Code can add the server from their MCP commands while supplying the same environment variable.

DEEPSEEK_REQUEST_TIMEOUT_MS controls the complete request lifetime, including response-body reads and streamed output. MCP_TOOL_RATE_LIMIT limits MCP tool invocations rather than DeepSeek spending.

Tools and capabilities

  • chat_completion: Send text or visual chat requests with thinking controls, JSON output, function tools, optional memory, and streaming aggregation.
  • create_response: Make stateless text or image Responses API calls with reasoning, structured output, function tools, apply_patch, and semantic stream aggregation.
  • completion: Run non-thinking FIM completion through the beta completions endpoint.
  • list_models: Inspect live models and their capabilities.
  • get_user_balance: Check account availability and balances.
  • upload_file, list_files, retrieve_file, and delete_file: Manage reusable DeepSeek image files.
  • reset_conversation and list_conversations: Clear or inspect local in-memory conversation IDs.

Inline images can be up to 32 MiB, uploaded files up to 64 MiB, and JSON request bodies up to 48 MiB. JPEG, PNG, GIF, and WebP are supported. FIM has a documented 4K output limit, and forced chat tool choices require thinking to be disabled.

Limitations and notes

DeepSeek’s frequency and presence penalty parameters are accepted for compatibility but ignored by the provider. Chat prefix completion and strict function tools use the beta chat endpoint automatically. stream_options requires streaming to be enabled.

The Files API is intended for reusable image inputs. Search and Fetch are not exposed as standalone MCP tools; only the Responses web_search option is available, and it is handled server-side by DeepSeek Pro. Check DeepSeek pricing before enabling search because its billing is separate from model-token charges.

Local conversations are in-memory and bounded, so they are not a persistent conversation store. Responses calls also do not retain history on the server.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about DeepSeek MCP Server

DeepSeek MCP Server is an MCP server that connects MCP clients to DeepSeek APIs for chat and visual completions, Responses calls, FIM completion, model discovery, balance checks, file management, and local conversation controls. It runs over stdio, requires a DeepSeek API key, and supports Node.js 20 or newer.

Install it by running it with `npx` and setting `DEEPSEEK_API_KEY`, for example `DEEPSEEK_API_KEY="your-key" npx -y deepseek-mcp-server`. Configure the same command and environment variable in an MCP client that supports stdio.

Send images using a URL, a supported base64 data URL, or a file ID returned by `upload_file`. JPEG, PNG, GIF, and WebP are supported, and image inputs can be passed to `chat_completion` or `create_response`.

It can maintain local in-memory chat conversations when `chat_completion` receives a `conversation_id`. Use `list_conversations` to inspect IDs and `reset_conversation` to clear one; `create_response` remains stateless and requires the caller to send the full history.

Related MCP servers

All in Knowledge & Memory All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewDeepSeek MCP Server AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/deepseek-mcp-server?style=directory)](https://allmcps.com/mcp/deepseek-mcp-server)
HTML Embed
<a href="https://allmcps.com/mcp/deepseek-mcp-server"><img src="https://allmcps.com/api/badge/deepseek-mcp-server?style=directory" alt="DeepSeek MCP Server on AllMCPs" /></a>