# injectshield MCP server

Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-bch1212-injectshield
- Repository: https://github.com/bch1212/injectshield
- Website: https://injectshield.dev

## Install
- Command: `npx -y @injectshield/mcp`
- Auth: Auth required by registry metadata

## Setup notes
- Package: Npm @injectshield/mcp v0.1.4
- Environment variable: INJECTSHIELD_API_KEY (required; secret)
- Environment variable: INJECTSHIELD_API_BASE (default https://api.injectshield.dev)
- The upstream registry signals required auth or secrets.

## Tools
Not captured

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.bch1212
- Version: 0.1.4
- Runtime: Npm
- Transports: STDIO
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: May 6, 2026
- Source: https://registry.modelcontextprotocol.io