Mentor (Deepseek)
This MCP server, developed by cyanheads, provides AI-powered mentorship capabilities through the Deepseek API. Built with TypeScript and leveraging the Model Context Protocol SDK, it offers tools for code review, design critique, writing feedback, and idea brainstorming. The implementation focuses on delivering expert second opinions and actionable insights to enhance LLM agent performance. It's particularly useful for developers, designers, and content creators seeking AI-assisted feedback and improvement suggestions, enabling use cases such as code quality enhancement, UI/UX refinement, documentation improvement, and feature ideation without directly interacting with the Deepseek API.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-02.
Scan details: Circle-IR · 2026-09-02 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/cyanheads/mentor-mcp-server
- Author type
- human
- Last scanned
- 2026-09-02
- Updated
- 2026-09-02
Use via MCP
Resolve Mentor (Deepseek) from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.