Search for information about a specific paper across all topic directories.
AI agents call extract_info to retrieve information from Render without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries information about papers without creating, modifying, deleting, or executing any operations. It fits the Read category as it has no side effects and only returns data. Severity is low because misuse would only result in accessing unintended information, not system damage or data loss.
From the tool's definition Tool name 'extract_info' combined with description 'Search for information about a specific paper across all topic directories' indicates data retrieval. The verb 'search' and 'extract information' are read-only operations with no side effects.
Documented attack patterns abuse exactly the kind of access extract_info gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Render, and nothing reaches the server without passing your rules. This is the rule we recommend for extract_info:
{
"version": "1",
"default": "deny",
"tools": {
"extract_info": {}
}
}extract_info 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 for information about a specific paper across all topic directories. It is categorised as a Read tool in the Render MCP Server, which means it retrieves data without modifying state.
Register the Render MCP server in PolicyLayer and add a rule for extract_info: 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 Render. Nothing to install.
extract_info 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 extract_info 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 extract_info. 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.
extract_info is provided by the Render MCP server (smartaces/render_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Render, 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.
7 Render tools catalogued and risk-classified — across an index of 43,000+ MCP servers.