Portfolio concentration metrics: HHI, Gini, top-5 share, biggest market.
AI agents call get_wallet_concentration 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 calculates analytical metrics about wallet portfolio composition using public Polymarket data. It performs no side effects, creates no data, executes no code, and deletes nothing.
From the tool's definition Tool name 'get_wallet_concentration' and description 'Portfolio concentration metrics: HHI, Gini, top-5 share, biggest market' indicate data retrieval only. Server description explicitly states 'Read-only MCP server'.
Attacks that exploit this kind of access
Portfolio concentration metrics: HHI, Gini, top-5 share, biggest market. 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_concentration: 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_concentration 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_concentration 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_concentration. 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_concentration 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 →