# com.decionis/mcp

> com.decionis/mcp — com-decionis-mcp. Use this tool when you need to enforce fail-closed policies for AI agent actions, ensuring secure and controlled decision-making. It solves problems related to unauthorized or unsafe actions by evaluating policies locally and providing native pre-tool hooks for customization. With input of AI agent actions and output of allowed or blocked decisions, use it in contexts where security and compliance are critical.

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

## Description

Fail-closed policy gate for AI agent actions, with local evaluation and native pre-tool hooks.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 0.1.1
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-19

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/com.decionis%2Fmcp)
- **Repository:** <https://github.com/decionis/agent-safe-pipeline>

## Use it

MCP endpoint published by the skill: `https://protocol.decionis.com/mcp`

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-decionis-mcp"
    }
  }
}
```

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