AI agents call econ.cot 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 returns historical CFTC Commitments of Traders data—a read-only operation that retrieves public market positioning information. There are no side effects, state changes, code execution, destructive operations, or financial transactions. The 'free/keyless' note confirms it is a passive data retrieval endpoint.
From the tool's definition Tool retrieves 'weekly futures positioning' data for a market, with description indicating it 'Match[es] a market by name'. No mutation, deletion, or external execution described.
Attacks that exploit this kind of access
CFTC Commitments of Traders (COT) — weekly futures positioning for a market (free/keyless). Match a market by name (e.g. \. 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 econ.cot: 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.
econ.cot 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 econ.cot 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 econ.cot. 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.
econ.cot 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 →