# MCP Shield

> The OpenWAF edge now reads MCP: method and tool policy, prompt-injection and credential-leak checks on tool calls and results, per-token limits.

Put your own MCP server behind OpenWAF and declare its path as an MCP endpoint: the edge reads every JSON-RPC message, applies a method and tool allowlist, inspects tool arguments and tool results for prompt injection and leaked credentials, and limits requests per token. Blocks are JSON-RPC errors with the id of the blocked request, so the session keeps working. It is part of AI Crawl Control, opt-in per endpoint, and starts in log mode.

See the [MCP Shield overview](https://developers.openwaf.dev/mcp-shield/) and [enable MCP Shield](https://developers.openwaf.dev/mcp-shield/enable/).