AI agents invoke db_mongodb_query to trigger actions in Infra Ops. 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.
Although 'find' is typically a read operation, the tool is described as executing a query, which runs code against an external system. MongoDB queries can include operators and JavaScript expressions that may have side effects or expose sensitive data at scale. On an infra-ops server with broad access, misuse could expose sensitive production data.
From the tool's definition 'Execute a MongoDB find query on a collection' — the tool runs a query operation against a live MongoDB database
Attacks that exploit this kind of access
Execute a MongoDB find query on a collection. It is categorised as a Execute tool in the Infra Ops MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Infra Ops MCP server in PolicyLayer and add a rule for db_mongodb_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 Infra Ops. Nothing to install.
db_mongodb_query 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 db_mongodb_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 db_mongodb_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.
db_mongodb_query is provided by the Infra Ops MCP server (skyvanguard/infra-ops-mcp). 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 →