Observed MCP server

mcp-honestbench

A deliberately dishonest MCP server that measures an agent system's honesty via deterministic, rule-driven lies across five modes, recording ground truth for scoring.

Security score

—/100

Awaiting a completed comparable scan.

Seven-category assessment pending: authentication, tool poisoning, prompt injection, dangerous capabilities, dependency risk, data exfiltration, and transport security.

Score history

Pending

Immutable methodology-versioned snapshots

Schema drift

Pending

No normalized tool schema observed

Fingerprint

Pending

Repository/package-backed identity

Public findings

No public findings recorded

This is not a safety claim. Check the coverage and revision status before relying on absence of findings.