A transparent MCP proxy that independently re-verifies tool-call claims instead of trusting them, paired with devmcp — the git/CI server it's proven against.
Enables deterministic security testing of AI agents that use tools by serving synthetic MCP environments with poisoned data, fake secrets, and privileged actions. Records agent tool calls and evaluates security invariants (e.g., canary leaks, forbidden access, approval binding) without an LLM judge or real systems.
A compact MCP server demonstrating explicit tool boundaries, least-privilege discovery, execution-time authorization, destructive-action confirmation, and metadata-only audit logs using a local note store.
A governed MCP server exposing 37 risk-checked tools with signed Ed25519 receipts on a Bitcoin-anchored ledger, failing closed if governance or receipt writing fails.
A stdio MCP server that audits other MCP servers over the live protocol. It connects to any MCP target (stdio or HTTP), lints every tool's schema for agent-usability, then actually calls the tools with deliberately broken inputs to see how the server handles them, and returns a 0–100 conformance score with a per-dimension breakdown rendered as Markdown.
This MCP server provides a stateful, resettable, verifiable API runtime that gates every tool call, enabling agents to run long workflows against provider-shaped environments without live provider write access. It records decisions, side effects, and outcome evidence for replayable, verifiable benchmark runs.