No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by ruixingshi · MCP Server · ★ 70
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is deepseek-thinker-mcp safe to install? View the security audit →
Deepseek Thinker MCP Server 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: (string): User's original prompt Returns: Structured text response containing the reasoning process Environment Configuration OpenAI API Mode Set the following environment variables: Ollama Mode Set the following environment variable: Usage Integration with AI Client, like Claude Desktop Add the following configuration to your : json { "mcpServers": { "deepseek-thinker": { "command": "npx",
| Stars | 70 |
| Forks | 17 |
| Language | JavaScript |
| Category | MCP Server |
| Quality Score | 71.9402732911802/100 |
| Open Issues | 5 |
| Last Updated | 2025-03-25 |
| Created | 2025-02-13 |
| Platforms | claude-code, cli, mcp, node |
| Est. Tokens | ~2k |
Explore other popular mcp server tools:
deepseek-thinker-mcp is 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.. It is categorized as a MCP Server with 70 GitHub stars.
deepseek-thinker-mcp is primarily written in JavaScript.
You can find installation instructions and usage details in the deepseek-thinker-mcp GitHub repository at github.com/ruixingshi/deepseek-thinker-mcp. The project has 70 stars and 17 forks, indicating an active community.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: