Load every tool in a named group at once (see list_tool_groups for names).
AI agents call load_tool_group 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 tool's function is informational: it enumerates and loads tool definitions from a pre-defined group. No data is created, modified, destroyed, or executed. The worst outcome of misuse is that an agent gains access to a list of available tools, which is a read-level risk in a local-first, user-controlled environment. Severity is low because the blast radius is limited to tool discovery within the user's own system.
From the tool's definition load_tool_group 'Load every tool in a named group at once' — this operation retrieves/queries tool metadata from a named group without modifying, deleting, or executing external operations.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Load every tool in a named group at once (see list_tool_groups for names). 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 load_tool_group: 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.
load_tool_group 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 load_tool_group 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 load_tool_group. 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.
load_tool_group 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 →