Elenchus
Elenchus is an adversarial verification system that orchestrates multi-round code review sessions between verifier and critic roles to systematically identify security, correctness, reliability, maintainability, and performance issues. It provides state management, context sharing, and automated verification loops through MCP tools, with advanced features like differential analysis for incremental verification, response caching to reduce token usage, function-level code chunking for large codebases, and quality safeguards including periodic full verification and confidence scoring. Designed for thorough code verification workflows where multiple AI agents collaborate to catch issues that single-pass reviews might miss.
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/jhlee0409/elenchus-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Elenchus 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.