AI agents call get_positions to retrieve information from Manifold without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns existing data (user positions in prediction markets) without creating, modifying, deleting, or executing any operations. It is a straightforward read/fetch operation with minimal risk if misused by an AI agent, as it only exposes market position information accessible to the querying user.
From the tool's definition Tool name is 'get_positions' and description states 'Get user positions across markets' — a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Get user positions across markets. It is categorised as a Read tool in the Manifold MCP Server, which means it retrieves data without modifying state.
Register the Manifold MCP server in PolicyLayer and add a rule for get_positions: 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.
get_positions 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 get_positions 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 get_positions. 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.
get_positions 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 →