Chain-of-Recursive-Thoughts
The CoRT MCP Server implements Chain-of-Recursive-Thoughts methodology that enhances AI reasoning by making models argue with themselves repeatedly across multiple rounds. Developed by KunihiroS based on PhialsBasement's original work, it features multi-LLM inference that randomly selects different models for each alternative response, enhanced evaluation prompts, and detailed logging capabilities. The server integrates with OpenAI and OpenRouter APIs, supporting various LLMs including GPT-4, Llama, Gemini, and Mistral models. It's particularly valuable for complex problem-solving scenarios where deeper, more thorough reasoning is required to generate optimal responses.
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 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · 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/kunihiros/cort-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Chain-of-Recursive-Thoughts 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.