Get the execution plan for an aggregation pipeline
AI agents call explain to retrieve information from MongoDB MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The explain operation is a diagnostic read-only tool that returns information about how MongoDB would execute an aggregation pipeline. It does not modify data, execute the pipeline against live data, or trigger external side effects. While it provides insights into the database structure and query plans, this information is non-sensitive metadata retrieval suitable for performance analysis.
From the tool's definition Tool name is 'explain' and description states it 'Get the execution plan for an aggregation pipeline' — this retrieves query metadata without modifying or executing the pipeline itself.
Attacks that exploit this kind of access
Get the execution plan for an aggregation pipeline. It is categorised as a Read tool in the MongoDB MCP Server MCP Server, which means it retrieves data without modifying state.
Register the MongoDB MCP Server MCP server in PolicyLayer and add a rule for explain: 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 MongoDB MCP Server. Nothing to install.
explain 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 explain 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 explain. 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.
explain is provided by the MongoDB MCP Server MCP server (ryaker/mongodb-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 →