get_ideas
AI agents call get_ideas to retrieve information from Metis Public Health without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name 'get_ideas' follows the Read pattern (get/fetch/retrieve). Given the Metis server keeps data local and operates as a research tool with specialist agents, this tool probably queries the user's indexed ideas without side effects. Absence of a description lowers confidence slightly, but the semantic meaning of 'get' and lack of destructive/write/execute language in the name points to Read.
From the tool's definition Tool name 'get_ideas' suggests retrieval or query operation; no description provided. Contextually, within a research companion that indexes PDFs and maintains local data, 'get_ideas' most likely retrieves or lists ideas from the user's stored knowledge base…
Attacks that exploit this kind of access
get_ideas. It is categorised as a Read tool in the Metis Public Health MCP Server, which means it retrieves data without modifying state.
Register the Metis Public Health MCP server in PolicyLayer and add a rule for get_ideas: 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 Metis Public Health. Nothing to install.
get_ideas 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 get_ideas 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 get_ideas. 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.
get_ideas is provided by the Metis Public Health MCP server (sveritg/metis_ph). 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 →