AI agents call econ.yield-curve 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 financial market data (Treasury yields and spreads) with no side effects, reversible actions, code execution, destructive operations, or financial transactions. It is a pure data retrieval operation, placing it firmly in the Read category.
From the tool's definition Tool retrieves 'Current US Treasury yield curve' and historical daily data from FRED; no parameters mentioned that would permit modification, deletion, or financial transactions. Described as a query/fetch operation providing market data.
Attacks that exploit this kind of access
Current US Treasury yield curve (1M–30Y constant-maturity yields) plus the 2s10s and 3m10y spreads and an inversion flag (recession signal). Daily data. Source: US Treasury via FRED. 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.yield-curve: 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.yield-curve 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.yield-curve 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.yield-curve. 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.yield-curve 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 →