AI agents call search_time_series_groups to retrieve information from BCRP-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches or lists available time series groups from Peru's Central Reserve Bank data. Searching is a non-destructive read operation with no side effects—it retrieves metadata about available data groups without modifying, deleting, or executing operations. The severity is low because misuse simply returns incorrect or excessive query results, not financial harm or data loss.
From the tool's definition Tool name 'search_time_series_groups' indicates searching/querying functionality within economic time series data. The server description confirms this is for 'search, explore, and analyze Peru's economic indicators'.
Attacks that exploit this kind of access
search_time_series_groups. It is categorised as a Read tool in the BCRP-MCP MCP Server, which means it retrieves data without modifying state.
Register the BCRP- MCP server in PolicyLayer and add a rule for search_time_series_groups: 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 BCRP-MCP. Nothing to install.
search_time_series_groups 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 search_time_series_groups 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 search_time_series_groups. 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.
search_time_series_groups is provided by the BCRP- MCP server (rodcar/bcrp-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 →