AI agents call get_named_query to retrieve information from Ignition without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about a named query (its SQL, parameters, database connection, and type) but does not execute the query, modify it, or delete it. It is a read-only operation that queries configuration data. The low severity reflects minimal blast radius—exposure of query metadata could inform attack planning but does not directly compromise data or systems.
From the tool's definition Tool name 'get_named_query' and description 'Get a named query's SQL, parameters, database connection, and type' indicate retrieval of query metadata and configuration without execution or modification.
Attacks that exploit this kind of access
Get a named query's SQL, parameters, database connection, and type. It is categorised as a Read tool in the Ignition MCP Server, which means it retrieves data without modifying state.
Register the Ignition MCP server in PolicyLayer and add a rule for get_named_query: 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 Ignition. Nothing to install.
get_named_query 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_named_query 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_named_query. 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_named_query is provided by the Ignition MCP server (nodeblue-ai/ignition-mcp-server). 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 →