Open positions sorted by current USD value, newest-priced first.
AI agents call get_wallet_positions to retrieve information from Polymarket Research without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves existing data about wallet positions without any capability to modify, delete, or execute actions. It is purely informational retrieval, fitting the 'Read' category for data queries with no side effects.
From the tool's definition Tool retrieves 'open positions sorted by current USD value' with no mention of modification, deletion, or execution capabilities. Server is explicitly described as 'Read-only MCP server'.
Attacks that exploit this kind of access
Open positions sorted by current USD value, newest-priced first. It is categorised as a Read tool in the Polymarket Research MCP Server, which means it retrieves data without modifying state.
Register the Polymarket Research MCP server in PolicyLayer and add a rule for get_wallet_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 Polymarket Research. Nothing to install.
get_wallet_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_wallet_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_wallet_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_wallet_positions is provided by the Polymarket Research MCP server (yoppav/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 →