# agenticrail-mcp

> agenticrail-mcp — msmd-rua-agenticrail-mcp. Use this tool when you need to enforce step validation and authorization for AI agents, allowing or denying actions before they are executed. It solves problems related to secure and transparent decision-making, providing a stateless and streamable HTTP interface for sealed, independently verifiable receipts. Ideal for use cases requiring auditable and trustworthy AI decision-making processes.

Canonical page: https://skillsregistry.net/skills/msmd-rua-agenticrail-mcp  
JSON: https://api.skillsregistry.net/v1/skills/msmd-rua-agenticrail-mcp

## Description

MCP server for the AgenticRail enforcement gate: ALLOW or DENY an AI agent's step before it runs, sealed into a signed, independently verifiable receipt. Stateless Streamable HTTP, protocol 2026-07-28.

## Trust

- **Trust score (0–1):** 0.96
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/MSMD-RUA/agenticrail-mcp)

## 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": "msmd-rua-agenticrail-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/msmd-rua-agenticrail-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/msmd-rua-agenticrail-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