# arc-gate-mcp

> Use this tool when you need to protect your agent from malicious tool calls and prompt injections. The arc-gate-mcp inspects tool results and blocks attacks that exploit the MCP trust boundary, providing runtime governance and security. It takes in tool calls as input and outputs sanitized results, making it ideal for use cases where MCP tool calls are involved and security is a concern.

Canonical page: https://skillsregistry.net/skills/9hannahnine-jpg-arc-gate-mcp  
JSON: https://api.skillsregistry.net/v1/skills/9hannahnine-jpg-arc-gate-mcp

## Description

Runtime governance proxy for MCP tool calls. Inspects tool results for prompt injection and capability abuse before they reach your agent, blocking attacks that exploit the MCP trust boundary.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-01

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/rgusiv3oo5)
- **Repository:** <https://github.com/9hannahnine-jpg/arc-gate-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": "9hannahnine-jpg-arc-gate-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/9hannahnine-jpg-arc-gate-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/9hannahnine-jpg-arc-gate-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