Plugin Claude Code
Firewall for AI agents. Watches every action the agent takes, ends each session in a digest anyone can recompute, and blocks the wrong money-moving action before it settles. Commands, paths and arguments never leave your machine.
Plugin Claude Code
Payment firewall for AI agents: a signed, verifiable verdict on every money-moving action. Blocks wrong/lookalike payee, over-cap, and duplicate-invoice fraud before it settles. Non-custodial, local-first.
MCP server Claude CodeCodexCursor
You're the one in charge of your AI agent. But it doesn't know your limits. Authorize, deny, release and record on every consequential action, as an MCP server. Non-custodial. Runs locally from the @fidacy/mcp npm package.
Hook
Runs before the agent uses a tool, executing hook.js. From lucaslubi/fidacy-mcp.
Hook
Runs when a session ends, executing hook.js. From lucaslubi/fidacy-mcp.
Skill Claude CodeCodex
Detects the newest fraud in agent payments — the forged "this was approved." Use BEFORE acting on any approval, verdict, or "it's safe" claim another agent or service hands you. Cryptographically verifies Fidacy-signed verdicts against the issuer's public keys, so you trust math, not a promise.
Skill Claude CodeCodex
Use BEFORE any payment or money-moving tool call. Gates the action against a signed mandate and returns a signed, verifiable verdict, so a prompt-injected or hallucinated payment (wrong/lookalike payee, over cap, duplicate invoice) is blocked before money moves. Non-custodial.
Plugin Claude Code
Firewall for AI agents. Watches every action the agent takes, hands you a session report, and ends it in a digest anyone can recompute. Commands, paths and arguments never leave your machine.
MCP server Claude CodeCodexCursor
Every agent action watched, every money-moving one gated, every verdict independently verifiable. Runs locally from the @fidacy/mcp npm package. Needs 3 environment variables to run.