Enables AI agents to develop Rocq proofs by checking files for diagnostics across proofs and running commands at specific positions for queries and debugging. It integrates with Rocq LSP and project configuration to support interactive proof workflows.
Enables MCP-compatible editors to run dialectical reasoning through thesis, antithesis, and synthesis, and to build verified code via a player-coach loop with independent review and session state.
MCP server for agentic interaction with the Lean theorem prover via LSP, providing tools for understanding, analyzing, and interacting with Lean projects.
Enables LLM agents to typecheck Narya files and develop proofs interactively by loading files into live sessions, inspecting and solving holes, searching for lemmas, and replaying edits.
Provides any MCP-capable coding agent with shared, warm language-server intelligence and project-local configuration, so diagnostics, definitions, references, hover, symbols, code actions, formatting, rename, and sync behave consistently across harnesses and sessions. This lets users switch agent tools without reconfiguring LSP integrations or falling back to CLI verification.