Gets the execution plan for a SQL query to understand how the database will execute it
AI agents call get-execution-plan to retrieve information from MCP Firebird without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Execution plan retrieval is a read-only diagnostic operation. It returns metadata about how the database optimizer will execute a query, without actually running the query against data or causing side effects. The tool serves analysis and performance tuning purposes only. While the MCP server context mentions 'manipulate data,' this specific tool does neither; it only inspects and reports on query strategy.
From the tool's definition Tool description states it 'Gets the execution plan for a SQL query to understand how the database will execute it' — a purely informational operation that retrieves query metadata without modifying, executing, or deleting data.
Documented attack patterns abuse exactly the kind of access get-execution-plan gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Firebird, and nothing reaches the server without passing your rules. This is the rule we recommend for get-execution-plan:
{
"version": "1",
"default": "deny",
"tools": {
"get-execution-plan": {}
}
}get-execution-plan 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.
Gets the execution plan for a SQL query to understand how the database will execute it. It is categorised as a Read tool in the MCP Firebird MCP Server, which means it retrieves data without modifying state.
Register the MCP Firebird MCP server in PolicyLayer and add a rule for get-execution-plan: 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 Firebird. Nothing to install.
get-execution-plan 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-execution-plan 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-execution-plan. 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-execution-plan is provided by the MCP Firebird MCP server (purodelphi/mcpfirebird). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 22 MCP Firebird tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
22 MCP Firebird tools catalogued and risk-classified — across an index of 42,500+ MCP servers.