Full-text search across articles. Set discover_sources=true to also search the web for new RSS feeds when local results are thin.
AI agents call crow_media_search to retrieve information from Crow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool queries existing article data and optionally discovers RSS feed sources via web search. No data is created, modified, deleted, or overwritten. No code execution or financial operations occur. This is a pure information retrieval operation, fitting the Read category with low severity due to minimal blast radius from misuse.
From the tool's definition Tool performs 'full-text search across articles' and optionally searches 'the web for new RSS feeds'. These are retrieval operations with no data modification, deletion, or execution of arbitrary code.
Documented attack patterns abuse exactly the kind of access crow_media_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Crow, and nothing reaches the server without passing your rules. This is the rule we recommend for crow_media_search:
{
"version": "1",
"default": "deny",
"tools": {
"crow_media_search": {}
}
} crow_media_search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Full-text search across articles. Set discover_sources=true to also search the web for new RSS feeds when local results are thin. It is categorised as a Read tool in the Crow MCP Server, which means it retrieves data without modifying state.
Register the Crow MCP server in PolicyLayer and add a rule for crow_media_search: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Crow. Nothing to install.
crow_media_search is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the crow_media_search rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for crow_media_search. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
crow_media_search is provided by the Crow MCP server (kh0pper/crow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Crow, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
576 Crow tools catalogued and risk-classified — across an index of 43,000+ MCP servers.