# mcp-armor

> mcp-armor — studiomeyer-io-mcp-armor. Use this tool when you need to protect your MCP servers from security threats, such as prompt injection and marketplace poisoning. The mcp-armor tool scans tool calls, validates Ed25519 manifest signatures, and blocks malicious vectors, providing a defense against multiple CVEs with minimal overhead. It is ideal for use cases requiring robust security measures, with a simple drop-in Rust sidecar implementation and low latency of under 5ms.

Canonical page: https://skillsregistry.net/skills/studiomeyer-io-mcp-armor  
JSON: https://api.skillsregistry.net/v1/skills/studiomeyer-io-mcp-armor

## Description

Drop-in Rust sidecar for MCP servers — scans tool calls for prompt injection, validates Ed25519 manifest signatures, blocks marketplace-poisoning vectors. <5ms p99 overhead. Defense against OX Security MCP advisory (10+ CVEs, April 2026).

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/studiomeyer-io/mcp-armor)

## 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": "studiomeyer-io-mcp-armor"
    }
  }
}
```

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