Unresolve a previously resolved market
AI agents call unresolve_market to permanently remove resources in Manifold — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Unresolving a market reverses a finalized state that users and participants have already acted upon (e.g., payouts may have been issued). This is a high-impact, potentially irreversible-in-practice operation affecting market integrity and participant expectations. It falls under Destructive because it overwrites a committed outcome, and misuse could cause significant harm to market participants and platform trust.
From the tool's definition 'Unresolve a previously resolved market' — reverses a finalized resolution state, undoing payouts and resolution outcomes that may have already been processed
Attacks that exploit this kind of access
Unresolve a previously resolved market. It is categorised as a Destructive tool in the Manifold MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Manifold MCP server in PolicyLayer and add a rule for unresolve_market: 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 Manifold. Nothing to install.
unresolve_market is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the unresolve_market 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 unresolve_market. 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.
unresolve_market is provided by the Manifold MCP server (manifold-mcp-server). 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 →