AI agents call market.data.screen to retrieve information from Rekko MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to screen/filter prediction market data based on context from the server's stated purpose ('market screening') and naming patterns of sibling tools. This is a retrieval/query operation with no inherent side effects. Severity is medium rather than low because market screening data could inform high-stakes financial decisions, though the tool itself does not execute trades or move capital.
From the tool's definition Tool name 'market.data.screen' combined with sibling tools ('market.data.get','market.data.list','market.data.history') and server description stating 'market screening' capability indicate this retrieves or filters market data.
Attacks that exploit this kind of access
market.data.screen. It is categorised as a Read tool in the Rekko MCP MCP Server, which means it retrieves data without modifying state.
Register the Rekko MCP server in PolicyLayer and add a rule for market.data.screen: 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 Rekko MCP. Nothing to install.
market.data.screen 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 market.data.screen 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 market.data.screen. 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.
market.data.screen is provided by the Rekko MCP server (rekko-ai/rekko-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 →