This MCP server implementation provides a bridge to DeepSeek's R1 reasoning engine, enabling AI assistants to leverage advanced cognitive modeling and multi-step reasoning capabilities. Developed by moyu6027, it uses FastMCP and integrates with the Infini API to process queries and generate structured reasoning outputs. The server focuses on error handling and formatting responses for seamless integration with other AI models like DeepSeek V3 or Claude. It's particularly useful for applications requiring sophisticated logical analysis, critical thinking, and complex problem-solving across various domains.
Cognium trust score
50%
Tier
Unverified
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.