AI agents call get_data to retrieve information from Mcp Bcrp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'get_data' and context (querying a statistical database alongside search and retrieval functions) strongly indicate read-only data fetching. The empty description reduces confidence slightly, but the pattern of sibling tools and server function (providing access to indicators and time-series data) makes misclassification as destructive, financial, or execute operations highly unlikely.
From the tool's definition Tool name is 'get_data' with empty description. Based on sibling tools (get_table, plot_chart, search_series) and server purpose (fetching time-series data from macroeconomic database), this is consistent with data retrieval operations.
Attacks that exploit this kind of access
get_data. It is categorised as a Read tool in the Mcp Bcrp MCP Server, which means it retrieves data without modifying state.
Register the Mcp Bcrp MCP server in PolicyLayer and add a rule for get_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 Mcp Bcrp. Nothing to install.
get_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_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_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_data is provided by the Mcp Bcrp MCP server (maykolmedrano/mcp_bcrp). 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 →