AI agents invoke execute_action to trigger actions in Metabase MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Metabase actions can perform a wide variety of side effects (API calls, database modifications, integrations with external systems). While the description doesn't specify destructiveness, the 'execute' semantics with parameterizable inputs means an AI agent could misuse this to trigger unintended consequences.
From the tool's definition Tool name is 'execute_action' and description states it 'Execute[s] a Metabase action with parameters'. The term 'execute' combined with ability to pass arbitrary parameters indicates the tool triggers external operations whose effects depend on the supplied…
Documented attack patterns abuse exactly the kind of access execute_action gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Metabase MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_action:
{
"version": "1",
"default": "deny",
"tools": {
"execute_action": {
"limits": [
{
"counter": "execute_action_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute_action stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute a Metabase action with parameters. It is categorised as a Execute tool in the Metabase MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Metabase MCP Server MCP server in PolicyLayer and add a rule for execute_action: 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 Metabase MCP Server. Nothing to install.
execute_action is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the execute_action 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 execute_action. 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.
execute_action is provided by the Metabase MCP Server MCP server (sazboxai/mcp_metabase). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Metabase 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.
9 Metabase MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.