get_project_categories
AI agents call get_project_categories 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.
This tool retrieves project metadata (categories) for display or filtering purposes. No modification, deletion, execution, or financial operations are indicated by the name or inferred from context. The empty description lowers confidence slightly, but the 'get_' prefix and categorical naming are strong signals of a read operation with minimal blast radius if misused by an agent.
From the tool's definition Tool name 'get_project_categories' follows a 'get_' prefix pattern consistent with retrieval operations (compare sibling 'get_' tools which are absent, but 'add_' verbs dominate the sibling list, suggesting 'get_' implies read-only queries).
Attacks that exploit this kind of access
get_project_categories. 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_project_categories: 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_project_categories 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_project_categories 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_project_categories. 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_project_categories 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 →