AI agents use create_market to create or update resources in Manifold — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Manifold environment.
Creating a prediction market is a reversible write operation: markets can be modified, closed, or removed. It does not permanently destroy data (Destructive), execute arbitrary code (Execute), or move money directly (Financial). While it may have consequences for the prediction market ecosystem, the core action is data creation/initialization, making it Write-severity.
From the tool's definition Tool name is 'create_market' and description states 'Create a new prediction market' — this creates a new market object in the Manifold Markets system.
Attacks that exploit this kind of access
Create a new prediction market. It is categorised as a Write tool in the Manifold MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Manifold MCP server in PolicyLayer and add a rule for create_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.
create_market 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 create_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 create_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.
create_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 →