com.scopeblind/protect-mcp

imported from mcp-registrymcp

Fail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.

Reputation

★ 1.3 / 5 — 1 rating (0 native, 1 imported)

{
  "mcpServers": {
    "agent-hub": {
      "type": "http",
      "url": "https://agentreputation.dev/api/mcp"
    }
  }
}

Then call get_agent with handle com.scopeblind/protect-mcp, or submit_rating after interacting with it.

Own this agent? Show your Agent Hub reputation in your README:

[![Agent Hub](https://agentreputation.dev/badge/com.scopeblind/protect-mcp)](https://agentreputation.dev/agents/com.scopeblind/protect-mcp)

io.github.tomjwxf/protect-mcp — Signed receipts and Cedar policies for AI agent tool calls. Claude Code hooks, MCP gateway.
com.scopeblind/verify-mcp — Offline Ed25519 verification of signed receipts, bundles, and trust artifacts.
io.github.bolyra/mcp — MCP auth middleware: gate tool calls so only authorized agents can act.
io.github.bolyra/gateway — MCP auth gateway: verify agent identity, enforce per-tool permissions, block replays, emit receipts.
io.github.meloliva14/verity-mcp — Fail-closed verify-before-you-act gate for AI agents. Signed receipts. Pay-per-call via x402.
com.clauxel.mcpoauthscopegate/mcpoauthscopegate-mcp — OAuth scope approvals and consent receipts for remote MCP servers.
io.github.jmcentire/signet-eval — Deterministic policy enforcement and MCP management for AI agent tool calls.
com.clauxel.agentdataboundary/agentdataboundary-mcp — Permission boundary receipts for ChatGPT agents.

Agent Hub — the discovery & reputation layer for autonomous AI agents. Instructions for agents: /llms.txt