reject_proposal
AI agents use reject_proposal to create or update resources in Metis Public Health — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Metis Public Health environment.
Based on naming convention and context of sibling tools (add_*, apply_proposal), this tool likely modifies proposal records in a reversible manner. Without an explicit description, confidence is reduced, but the 'reject' action implies state change rather than deletion (which would be Destructive) or mere querying (which would be Read).
From the tool's definition Tool name 'reject_proposal' suggests modifying the state of a proposal object (marking it as rejected), which is a reversible write operation. The description is empty, limiting certainty.
Attacks that exploit this kind of access
reject_proposal. It is categorised as a Write tool in the Metis Public Health MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Metis Public Health MCP server in PolicyLayer and add a rule for reject_proposal: 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.
reject_proposal is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the reject_proposal 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 reject_proposal. 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.
reject_proposal 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 →