# com.scopeblind/protect-mcp

> Use this tool when you need to secure AI agent tool calls with signed receipts and Cedar policies, solving authentication and authorization problems in AI interactions. It provides a reliable interface for Claude Code hooks and MCP gateway integration, accepting tool call requests as input and outputting verified receipts. Use it in contexts where secure and authenticated AI tool interactions are critical.

Canonical page: https://skillsregistry.net/skills/com-scopeblind-protect-mcp  
JSON: https://api.skillsregistry.net/v1/skills/com-scopeblind-protect-mcp

## Description

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

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** unverified

## Facts

- **Version:** 0.5.4
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-07-16

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/com.scopeblind%2Fprotect-mcp)
- **Repository:** <https://github.com/scopeblind/scopeblind-gateway>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "com-scopeblind-protect-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/com-scopeblind-protect-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/com-scopeblind-protect-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt