AI agents call search_content to retrieve information from Everything without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description reducing confidence slightly, the tool name and server context (file search engine) strongly indicate this searches file contents without modifying data. Classified as Read with low severity since content search has no side effects or blast radius when invoked by an AI agent.
From the tool's definition Tool name 'search_content' combined with sibling tools 'search_files' and 'search_files_advanced' on a file search server indicates a query/retrieval operation. The Everything SDK context and absence of modification verbs support read-only classification.
Documented attack patterns abuse exactly the kind of access search_content gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Everything, and nothing reaches the server without passing your rules. This is the rule we recommend for search_content:
{
"version": "1",
"default": "deny",
"tools": {
"search_content": {}
}
}search_content 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.
search_content. It is categorised as a Read tool in the Everything MCP Server, which means it retrieves data without modifying state.
Register the Everything MCP server in PolicyLayer and add a rule for search_content: 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 Everything. Nothing to install.
search_content 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 search_content 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 search_content. 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.
search_content is provided by the Everything MCP server (peterparker57/everything-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Everything, 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.
4 Everything tools catalogued and risk-classified — across an index of 43,000+ MCP servers.