Retrieve a single row by its key field value
AI agents call get_by_id to retrieve information from MCP Data Catalog without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data from a CSV-backed dataset without modifying, executing code, deleting, or incurring financial effects. It is a simple lookup operation analogous to a SELECT query with a WHERE clause on a primary key. The blast radius of misuse is minimal—an attacker could extract sensitive data but cannot corrupt, delete, or execute arbitrary operations.
From the tool's definition Tool name is 'get_by_id' and description states 'Retrieve a single row by its key field value' — a pure read operation with no modification or deletion.
Attacks that exploit this kind of access
Retrieve a single row by its key field value. It is categorised as a Read tool in the MCP Data Catalog MCP Server, which means it retrieves data without modifying state.
Register the MCP Data Catalog MCP server in PolicyLayer and add a rule for get_by_id: 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 Data Catalog. Nothing to install.
get_by_id 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_by_id 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_by_id. 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_by_id is provided by the MCP Data Catalog MCP server (mikeored/catalog-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 →