Get custom metrics for a project
AI agents call lightdash_get_custom_metrics to retrieve information from Lightdash MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries custom metrics data from a Lightdash project. It performs a read-only operation consistent with data fetching and falls squarely within the Read category. The blast radius is minimal as it only accesses existing analytics metadata without modifying, executing, or deleting anything.
From the tool's definition Tool name contains 'get' and description states 'Get custom metrics for a project' — these indicate data retrieval with no side effects.
Documented attack patterns abuse exactly the kind of access lightdash_get_custom_metrics gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Lightdash MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for lightdash_get_custom_metrics:
{
"version": "1",
"default": "deny",
"tools": {
"lightdash_get_custom_metrics": {}
}
} lightdash_get_custom_metrics is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get custom metrics for a project. It is categorised as a Read tool in the Lightdash MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Lightdash MCP Server MCP server in PolicyLayer and add a rule for lightdash_get_custom_metrics: 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 Lightdash MCP Server. Nothing to install.
lightdash_get_custom_metrics 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 lightdash_get_custom_metrics 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 lightdash_get_custom_metrics. 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.
lightdash_get_custom_metrics is provided by the Lightdash MCP Server MCP server (syucream/lightdash-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Lightdash MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
13 Lightdash MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.