# MCPShield

> Use this tool when you need to protect your MCP infrastructure from security threats and ensure compliance. MCPShield acts as a reverse proxy, monitoring and enforcing security policies in real-time, detecting and blocking malicious activities such as prompt injection attempts. It takes in client requests and server responses as inputs, filtering sensitive data and blocking unauthorized requests, while providing audit logs as output.

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

## Description

MCPShield is a security-focused reverse proxy that sits between MCP clients and servers, providing real-time monitoring and enforcement of security policies. It detects prompt injection attempts, filters sensitive data from tool call responses, and blocks unauthorized outbound requests. The platform supports custom rule definitions and provides audit logging for compliance and incident response.

## Trust

- **Trust score (0–1):** 0.99
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/mcpshield-dev-mcpshield)
- **Repository:** <https://github.com/mcpshield-dev/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-dev-mcpshield"
    }
  }
}
```

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