Top holders of a Polymarket market, grouped by outcome token (conditionId). Each holder: wallet, trader name, position size, outcome index, and verified flag. Reveals concentration and smart-money positioning per outcome — the holder-side complement to predict.trades (flow) and predict.whales (la...
AI agents call predict.holders to retrieve information from Mcp 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 publicly observable market data (holder information and positions) without modifying state, executing code, or moving funds. It is purely informational, analogous to a blockchain data API that surfaces existing on-chain information.
From the tool's definition Tool description explicitly states 'Read-only' and retrieves data about market holders: wallet addresses, trader names, position sizes, outcome indices, and verified flags. No modification, deletion, execution, or financial transaction occurs.
Attacks that exploit this kind of access
Top holders of a Polymarket market, grouped by outcome token (conditionId). Each holder: wallet, trader name, position size, outcome index, and verified flag. Reveals concentration and smart-money positioning per outcome — the holder-side complement to predict.trades (flow) and predict.whales (large trades). Read-only. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for predict.holders: 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 Mcp. Nothing to install.
predict.holders 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 predict.holders 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 predict.holders. 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.
predict.holders is provided by the MCP server (@2sio/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 →