Historical daily exchange-rate series from the European Central Bank (via Frankfurter) with computed stats. base (default USD), start (YYYY-MM-DD, required), optional end (default latest), symbols (comma-separated target codes), amount. Range capped at 366 days. Returns per-currency first/last/mi...
AI agents call fx.timeseries 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 retrieves historical exchange rate data and computes statistics on it. It is purely a read/query operation with no side effects — it does not move money, execute code, or modify any data. Despite being on a pay-per-call server, the tool itself only fetches and returns financial data, it does not execute trades or financial transactions.
From the tool's definition Historical daily exchange-rate series from the European Central Bank (via Frankfurter) with computed stats... Returns per-currency first/last/min/max/mean and absolute + % change, plus the full daily series.
Attacks that exploit this kind of access
Historical daily exchange-rate series from the European Central Bank (via Frankfurter) with computed stats. base (default USD), start (YYYY-MM-DD, required), optional end (default latest), symbols (comma-separated target codes), amount. Range capped at 366 days. Returns per-currency first/last/min/max/mean and absolute + % change, plus the full daily series. Business days 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 fx.timeseries: 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.
fx.timeseries 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 fx.timeseries 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 fx.timeseries. 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.
fx.timeseries 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 →