# mcp

> mcp — decionis-mcp. Use this tool when you need to evaluate and control AI agent actions against a set of predefined policies. It solves problems related to ensuring compliance and security by checking actions against a policy file (DECIONIS_POLICY.md) before execution. It takes in agent actions and policy files as inputs and outputs controlled actions, ideal for use in git-based development environments.

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

## Description

Decionis MCP policy tools and native Claude Code, Codex, and Copilot execution hooks — evaluate agent actions against DECIONIS_POLICY.md before they run. npx -y --package=@decionis/mcp decionis-mcp

## Trust

- **Trust score (0–1):** 1.00
- **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/decionis/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": "decionis-mcp"
    }
  }
}
```

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