Injectshield
MCP server bch1212/injectshield/io.github.bch1212/injectshield homepage
Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.From the repository description
claude mcp add injectshield -- npx -y @injectshield/mcpAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.