Score how much two wallets trade together.
AI agents call correlate_wallets 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 retrieves and analyzes trading patterns between wallets using public blockchain data. It performs correlational analysis without modifying, deleting, or executing external operations. The read-only server design confirms no side effects. Blast radius is minimal—worst case reveals public trading patterns without enabling harm.
From the tool's definition Tool description states 'Score how much two wallets trade together' — a query/analysis operation. Server description emphasizes 'Read-only MCP server' and notes tools are 'backed by public APIs and an optional SQLite cache', indicating data retrieval only.
Attacks that exploit this kind of access
Score how much two wallets trade together. 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 correlate_wallets: 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.
correlate_wallets 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 correlate_wallets 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 correlate_wallets. 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.
correlate_wallets 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 →