Loomal

injectshield

MCP server by github.com/bch1212/injectshield

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

0 starsnpm: @injectshield/mcp

About injectshield

injectshield is an MCP (Model Context Protocol) server published by bch1212 in the official MCP registry, listed under Security on Loomal. Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.

It ships as an npm package (@injectshield/mcp), so any MCP client that can launch a local process can run it.

Development happens in the open at github.com/bch1212/injectshield.

Use injectshield with your agent

Claude Code · one command
claude mcp add injectshield -- npx -y @injectshield/mcp
Claude Desktop, Cursor & other MCP clients · config
{
  "mcpServers": {
    "injectshield": {
      "command": "npx",
      "args": [
        "-y",
        "@injectshield/mcp"
      ]
    }
  }
}
npm@injectshield/mcp

Frequently asked questions

What is injectshield?
injectshield is an MCP (Model Context Protocol) server by bch1212 in the Security category. Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.
How do I connect injectshield to Claude, Cursor, or another MCP client?
Install injectshield from its npm package (@injectshield/mcp) and register it under "mcpServers" in your client's MCP configuration — for example claude_desktop_config.json or Cursor's mcp.json — then restart the client.
Is injectshield open source?
Yes — the source code is public at github.com/bch1212/injectshield.
Can AI agents pay to use injectshield?
Not yet through Loomal — injectshield is listed as a free directory entry. If its maintainer verifies ownership, they can set per-call USDC pricing that agents pay over x402, with settlement on Base.

Listing data from the official MCP registry and GitHub, refreshed periodically. Not affiliated with the maintainer unless claimed. Maintain injectshield? Claim this listing free by verifying GitHub ownership, or contact us.