get_activity
AI agents call get_activity to retrieve information from Polymarket without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves activity data from Polymarket's public CLOB without modification or execution capabilities. The server is explicitly read-only, and the naming convention aligns with other data retrieval tools. No financial transactions, code execution, or destructive operations are implied. Severity is low as misuse would only expose already-public market data.
From the tool's definition Server description explicitly states 'read-only interface' and tool name 'get_activity' follows the pattern of sibling tools (get_book, get_positions, get_price, etc.) which are all retrieval operations.
Attacks that exploit this kind of access
get_activity. It is categorised as a Read tool in the Polymarket MCP Server, which means it retrieves data without modifying state.
Register the Polymarket MCP server in PolicyLayer and add a rule for get_activity: 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 Polymarket. Nothing to install.
get_activity 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_activity 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_activity. 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_activity is provided by the Polymarket MCP server (pr1m8/polymarket-mcp). 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 →