Atlas / MCP servers / kuon-dev / DeepSeek Reasoner

DeepSeek ReasonerSAFE

mcp/kuon-dev/deepseek-reasoner

Enhanced version of "Sequential Thinking" MCP

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
1 1r · 0w · 0d
Transport
stdio
License
MIT
Stars
33
01

Overview

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

A tool for advanced reasoning and reflection using the Gemini API.

Requirements

  • Node.js 20.17 or higher
  • Gemini API key
  • Open Router API key

Installation

  1. Clone the repository:
git clone [email protected]:Kuon-dev/advanced-reason-mcp.git
cd advanced-reason-mcp
  1. Install dependencies
npm install

Building

Build the project using:

node ./bin/build.mjs

This will create the necessary files in the dist directory.

Configuration

The tool can be configured through the claude_desktop_config.json settings in your project configuration:

{
"advanced-reflection-reason": {
"command": "node",
"args": ["/path/to/your/advanced-reason-mcp/dist/index.js"],
"env": {
"GEMINI_API_KEY": "your-api-key-here",
"OPENROUTER_API_KEY": "your-api-key-here",
"OPENROUTER_MODEL": "your-selected-model-here"
}
}
}

OPENROUTER_MODEL env variable is optional. Defaults to deepseek/deepseek-r1:free if left empty.

Limitations

  • AI models does not have access to your project context, do be aware
  • If the task is too complex, it is possible for the content to get really long, in which the MCP will timeout and return no response

License

This project is MIT licensed.

You can create your own project and modifying it freely without notifying me

Read from source at commit edbb0dd7dd4fOBSERVED · 2026-10-08
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 advanced-reason-mcp --env GEMINI_API_KEY=${GEMINI_API_KEY} --env OPENROUTER_API_KEY=${OPENROUTER_API_KEY} -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "advanced-reason-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "GEMINI_API_KEY": "${GEMINI_API_KEY}",
        "OPENROUTER_API_KEY": "${OPENROUTER_API_KEY}"
      }
    }
  }
}
03

Exposed tools (1)

1 read · 0 write · 0 destructive.

ToolRiskDescription
combined-sequential-thinkingreadA powerful tool for structured, methodical problem-solving through OpenRouter-powered sequential thinking. This tool generates thoughts following a specific 5-step reasoning structure: 1. Identify the user
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)

LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@google/genai, @modelcontextprotocol/sdk, esbuild, ollama, openai, os, path, zod
Why it matters. 12 dependency range(s) float
Fix. pin exact versions or ship a lockfile
INFOPrompt injection · prompt.credential_read · CWE-94, CWE-1427
README.md:13
- Open Router API key
Why it matters. asks the agent to read credentials

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha edbb0dd7dd4ffull audit observations/trust-audit/mcp-server/kuon-dev__deepseek-reasoner.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
2026-10-08edbb0dd7dd4fSAFEB89first audit
06

Questions

What is the DeepSeek Reasoner MCP server?

Enhanced version of "Sequential Thinking" MCP

What tools does DeepSeek Reasoner 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 Reasoner 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 Reasoner need?

It reads GEMINI_API_KEY and OPENROUTER_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 Reasoner run?

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

How current is this page?

The grade is for one exact copy of the source (edbb0dd7dd4f), read on 2026-10-08. The repository is watched and re-audited when it changes.

Advertisement