# Praesidio

> Use this tool when you need to protect MCP clients and servers from security threats, such as tool poisoning and credential leaks. Praesidio acts as a security proxy, providing runtime firewall protection and advanced threat analysis through LLM-powered detection and behavioral anomaly monitoring. It offers a live security dashboard and honeypot traps, making it ideal for use cases requiring robust security measures against supply chain tampering and Unicode attacks.

Canonical page: https://skillsregistry.net/skills/mcpshield  
JSON: https://api.skillsregistry.net/v1/skills/mcpshield

## Description

Acts as a security proxy between MCP clients and servers, providing runtime firewall protection against tool poisoning, credential leaks, Unicode attacks, and supply chain tampering. Includes LLM-powered threat analysis, behavioral anomaly detection, honeypot traps, and a live security dashboard.

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/mcpshield)

## 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": "mcpshield"
    }
  }
}
```

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