AI agents call get_time_series_data 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.
The tool retrieves time series economic data from Peru's Central Reserve Bank. Despite the empty description, the name 'get' and the server's stated purpose of enabling agents to 'search, explore, and analyze' economic indicators confirms this is a read-only data retrieval operation. No side effects, modifications, or destructive actions are implied.
From the tool's definition Tool name is 'get_time_series_data' with empty description; server context describes 'access to economic and financial time series data' with verbs 'search, explore, and analyze' indicating data retrieval without modification.
Attacks that exploit this kind of access
get_time_series_data. 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 get_time_series_data: 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.
get_time_series_data 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 get_time_series_data 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 get_time_series_data. 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.
get_time_series_data 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 →