Run a read-only MongoDB aggregation pipeline. Use collection-schema first for field names, relationships, and known gotchas.
AI agents invoke aggregate to trigger actions in Askdb. 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.
While the tool does not modify data (ruling out Write/Destructive) and is not financial, MongoDB aggregation pipelines constitute code execution against the database server. The ability to construct complex multi-stage pipelines with operators like $lookup, $facet, $bucket, and custom expressions means the effect depends heavily on the arguments supplied by the agent.
From the tool's definition Tool description states 'Run a read-only MongoDB aggregation pipeline.' Aggregation pipelines can execute arbitrary transformations, filtering, grouping, and computed operations on database data.
Documented attack patterns abuse exactly the kind of access aggregate gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Askdb, and nothing reaches the server without passing your rules. This is the rule we recommend for aggregate:
{
"version": "1",
"default": "deny",
"tools": {
"aggregate": {
"limits": [
{
"counter": "aggregate_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}aggregate 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.
Run a read-only MongoDB aggregation pipeline. Use collection-schema first for field names, relationships, and known gotchas. It is categorised as a Execute tool in the Askdb MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Askdb MCP server in PolicyLayer and add a rule for aggregate: 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 Askdb. Nothing to install.
aggregate 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 aggregate 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 aggregate. 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.
aggregate is provided by the Askdb MCP server (mgorabbani/askdb). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Askdb, 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.
10 Askdb tools catalogued and risk-classified — across an index of 43,000+ MCP servers.