AI agents call get_survey to retrieve information from BLS MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a straightforward data retrieval operation (retrieve metadata) with no side effects, reversible modifications, code execution, destructive operations, or financial implications. It matches the 'Read' category definition as a simple get/fetch operation that queries and returns information without altering any data.
From the tool's definition Tool 'get_survey' retrieves metadata for a single BLS survey by abbreviation. The description explicitly indicates retrieval of survey metadata with no indication of modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Retrieve metadata for a single BLS survey by its abbreviation. It is categorised as a Read tool in the BLS MCP MCP Server, which means it retrieves data without modifying state.
Register the BLS MCP server in PolicyLayer and add a rule for get_survey: 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 BLS MCP. Nothing to install.
get_survey 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_survey 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_survey. 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_survey is provided by the BLS MCP server (larasrinath/bls_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 →