ModelsAtlas
Explore
Atlas / MCP servers / 66julienmartin / Deepseek R1

Deepseek R1SAFE

mcp/66julienmartin/deepseek-r1
MCP server by 66julienmartin · Audited 2026-10-07
⚑ Report / re-scanSource ↗

A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
1 1r · 0w · 0d
Transport
stdio
License
MIT
Stars
68
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://mseep.ai/app/66julienmartin-mcp-server-deepseek-r1)

A Model Context Protocol (MCP) server implementation for the Deepseek R1 language model. Deepseek R1 is a powerful language model optimized for reasoning tasks with a context window of 8192 tokens.

Why Node.js? This implementation uses Node.js/TypeScript as it provides the most stable integration with MCP servers. The Node.js SDK offers better type safety, error handling, and compatibility with Claude Desktop.

Quick Start

Installing manually

# Clone and install
git clone https://github.com/66julienmartin/MCP-server-Deepseek_R1.git
cd deepseek-r1-mcp
npm install

# Set up environment
cp .env.example .env  # Then add your API key

# Build and run
npm run build

Prerequisites

  • Node.js (v18 or higher)
  • npm
  • Claude Desktop
  • Deepseek API key

Model Selection

By default, this server uses the deepseek-R1 model. If you want to use DeepSeek-V3 instead, modify the model name in src/index.ts:

// For DeepSeek-R1 (default)
model: "deepseek-reasoner"

// For DeepSeek-V3
model: "deepseek-chat"

Project Structure

deepseek-r1-mcp/
├── src/
│   ├── index.ts             # Main server implementation
├── build/                   # Compiled files
│   ├── index.js
├── LICENSE
├── README.md
├── package.json
├── package-lock.json
└── tsconfig.json

Configuration

  1. Create a .env file:
DEEPSEEK_API_KEY=your-api-key-here
  1. Update Claude Desktop configuration:
{
"mcpServers": {
"deepseek_r1": {
"command": "node",
"args": ["/path/to/deepseek-r1-mcp/build/index.js"],
"env": {
"DEEPSEEK_API_KEY": "your-
Read from source at commit 892c29c45f9bOBSERVED · 2026-10-07
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code
claude mcp add deepseek_r1 --env DEEPSEEK_API_KEY=${DEEPSEEK_API_KEY} -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "deepseek_r1": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "DEEPSEEK_API_KEY": "${DEEPSEEK_API_KEY}"
      }
    }
  }
}
03

Exposed tools (1)

1 read · 0 write · 0 destructive.

ToolRiskDescription
deepseek_r1readGenerate text using DeepSeek R1 model
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (2)

LOWInventory / provenance · inv.hidden_file · CWE-1104
.env.exemple
.env.exemple
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
dotenv, openai, @types/node, typescript
Why it matters. 4 dependency range(s) float
Fix. pin exact versions or ship a lockfile

Gates applied: no_behavioural_pass.

Audited 2026-10-07 · audit v0.4.1 · source sha 892c29c45f9bfull audit observations/trust-audit/mcp-server/66julienmartin__deepseek-r1.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-07892c29c45f9bSAFEB89first audit
06

Questions

What is the Deepseek R1 MCP server?

A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)

What tools does Deepseek R1 expose?

1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Deepseek R1 safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does Deepseek R1 need?

It reads DEEPSEEK_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does Deepseek R1 run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as deepseek_r1 at 1.0.0.

How current is this page?

The grade is for one exact copy of the source (892c29c45f9b), read on 2026-10-07. The repository is watched and re-audited when it changes.

Advertisement