partner_health
AI agents call partner_health to retrieve information from Supply Ops Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on naming convention and the diagnostic nature of all sibling tools on this server, 'partner_health' most likely retrieves or queries partner metrics/status without modifying data. No evidence of side effects, destructive actions, or financial operations. The empty description and generic name prevent higher confidence.
From the tool's definition Tool name 'partner_health' suggests monitoring/querying partner status. Context: supply-ops-agent performs 'bid rate analysis, IVT detection, and ads.txt compliance' — all diagnostic/read operations.
Attacks that exploit this kind of access
partner_health. It is categorised as a Read tool in the Supply Ops Agent MCP Server, which means it retrieves data without modifying state.
Register the Supply Ops Agent MCP server in PolicyLayer and add a rule for partner_health: 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 Supply Ops Agent. Nothing to install.
partner_health 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 partner_health 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 partner_health. 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.
partner_health is provided by the Supply Ops Agent MCP server (mpessis/supply-ops-agent). 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 →