Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.
Install
Run one of the commands below, then add the client config underneath.
npx -y @injectshield/mcpClient configuration
Paste into Claude Desktop, Cursor (mcp.json), VS Code or any MCP client, then restart the client.
{
"mcpServers": {
"injectshield": {
"command": "npx",
"args": [
"-y",
"@injectshield/mcp"
]
}
}
}About this server
Injectshield is listed in the Developer Tools category of the MCPNav directory. It is distributed as npm and can be loaded by any client that speaks the Model Context Protocol.
Typical uses include giving your assistant scoped access to the corresponding service so it can answer questions and take actions with real data instead of guessing. Always review what a server can access before you enable it — see our MCP security guide.
Frequently asked questions
What is the Injectshield MCP server?＋
Injectshield is an MCP server by bch1212. Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.
How do I install Injectshield?＋
Install it with: npx -y @injectshield/mcp. Then add the JSON config to your client's MCP settings and restart the client.
Is Injectshield free to use?＋
The MCP server itself is free to install. The source is public on https://github.com/bch1212/injectshield. Any third-party API it calls (such as a search or maps API) may require its own key and billing.
Which clients support Injectshield?＋
Any MCP-compatible client can use it, including Claude Desktop, Cursor, VS Code, Windsurf and custom agents.