find_plugins_for_task
AI agents call find_plugins_for_task to retrieve information from Sage MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'find' verb typically indicates searching or querying without modification. No evidence suggests data creation, deletion, code execution, or financial impact. However, confidence is moderate due to the empty description—if the tool unexpectedly triggers plugin downloads or installations, it could be Execute instead. The empty description warrants a slight confidence reduction from 0.9 to 0.7.
From the tool's definition Tool name 'find_plugins_for_task' suggests a query/search operation to locate plugins matching specified criteria. The description is empty, limiting certainty, but the naming pattern aligns with Read operations (find, search).
Attacks that exploit this kind of access
find_plugins_for_task. It is categorised as a Read tool in the Sage MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Sage MCP Server MCP server in PolicyLayer and add a rule for find_plugins_for_task: 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 Sage MCP Server. Nothing to install.
find_plugins_for_task 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 find_plugins_for_task 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 find_plugins_for_task. 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.
find_plugins_for_task is provided by the Sage MCP Server MCP server (waggle-sensor/sage-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →