Atlas / MCP servers / ruixingshi / Deepseek Thinker

Deepseek ThinkerSAFE

mcp/ruixingshi/deepseek-thinker

A MCP provider Deepseek reasoning content to MCP-enabled AI Clients, like Claude Desktop. Supports access to Deepseek's CoT from the Deepseek API service or a local Ollama server.

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
1 1r · 0w · 0d
Transport
stdio
License
—
Stars
69
01

Overview

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

[](https://smithery.ai/server/@ruixingshi/deepseek-thinker-mcp)

A MCP (Model Context Protocol) provider Deepseek reasoning content to MCP-enabled AI Clients, like Claude Desktop. Supports access to Deepseek's thought processes from the Deepseek API service or from a local Ollama server.

Core Features

  • 🤖 Dual Mode Support
  • OpenAI API mode support
  • Ollama local mode support
  • 🎯 Focused Reasoning
  • Captures Deepseek's thinking process
  • Provides reasoning output

Available Tools

get-deepseek-thinker

  • Description: Perform reasoning using the Deepseek model
  • Input Parameters:
  • originPrompt (string): User's original prompt
  • Returns: Structured text response containing the reasoning process

Environment Configuration

OpenAI API Mode

Set the following environment variables:

API_KEY=
BASE_URL=

Ollama Mode

Set the following environment variable:

USE_OLLAMA=true

Usage

Integration with AI Client, like Claude Desktop

Add the following configuration to your claude_desktop_config.json:

{
"mcpServers": {
"deepseek-thinker": {
"command": "npx",
"args": [
"-y",
"deepseek-thinker-mcp"
],
"env": {
"API_KEY": "",
"BASE_URL": ""
}
}
}
}

Using Ollama Mode

{
"mcpServers": {
"deepseek-thinker": {
"command": "npx",
"args": [
"-y",
"deepseek-thinker-mcp"
],
"env": {
"USE_OLLAMA": "true"
}
}
}
}

Local Server Configuration

{
"mcpServers": {
"deepseek-thinker": {
Read from source at commit da3e6b1124e9OBSERVED · 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.

claude-code
claude mcp add deepseek-thinker-mcp -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "deepseek-thinker-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  }
}
03

Exposed tools (1)

1 read · 0 write · 0 destructive.

ToolRiskDescription
get-deepseek-thinkerreadthink with deepseek
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 & inventoryWARN
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 (4)

MEDIUMInventory / provenance · inv.binary · CWE-1104
.DS_Store
.DS_Store
Why it matters. a compiled or binary member cannot be reviewed from source
Fix. ship source, or explain the binary in the README
LOWInventory / provenance · inv.hidden_file · CWE-1104
.DS_Store
.DS_Store
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.no_license · CWE-1104
Why it matters. no LICENSE file and no repo licence
Fix. add a licence
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@modelcontextprotocol/sdk, ollama, openai, os, path, zod, zod-to-json-schema, @types/node
Why it matters. 9 dependency range(s) float
Fix. pin exact versions or ship a lockfile

Gates applied: no_behavioural_pass, no_license.

Audited 2026-10-07 · audit v0.4.1 · source sha da3e6b1124e9full audit observations/trust-audit/mcp-server/ruixingshi__deepseek-thinker.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
2026-10-07da3e6b1124e9SAFEB89first audit
06

Questions

What is the Deepseek Thinker MCP server?

A MCP provider Deepseek reasoning content to MCP-enabled AI Clients, like Claude Desktop. Supports access to Deepseek's CoT from the Deepseek API service or a local Ollama server.

What tools does Deepseek Thinker 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 Thinker 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 Thinker need?

No credential environment variables were found in its source, so it appears to need none.

How does Deepseek Thinker run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as deepseek-thinker-mcp at 1.0.2.

How current is this page?

The grade is for one exact copy of the source (da3e6b1124e9), read on 2026-10-07. The repository is watched and re-audited when it changes.

Advertisement