mongo_aggregate · Mcp Database MCP: Risk & Policy

WHAT IT DOES

What mongo_aggregate does on Mcp Database

AI agents invoke mongo_aggregate to trigger actions in Mcp Database. 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.

WHY IT NEEDS A POLICY

Why mongo_aggregate needs a policy

Although mongo_aggregate is primarily used for querying and analyzing data (which could suggest Read category), MongoDB aggregation pipelines are flexible enough to execute complex operations beyond simple data retrieval. They support stages like $out and $merge that write data, and $function that executes arbitrary JavaScript. This makes the tool's behavior dependent on its arguments—a hallmark of Execute category.

From the tool's definition Tool description: 'Run aggregation pipeline on a MongoDB collection'. Aggregation pipelines are arbitrary computational operations that can read, filter, compute, and stage-transform data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mongo_aggregate Rate-limited

mongo_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "mongo_aggregate": {
      "limits": [
        {
          "counter": "mongo_aggregate_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Mcp Database, so you can run agents against it safely.

FAQ

Questions about mongo_aggregate

What does the mongo_aggregate tool do? +

Run aggregation pipeline on a MongoDB collection. It is categorised as a Execute tool in the Mcp Database MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on mongo_aggregate? +

Register the Mcp Database MCP server in PolicyLayer and add a rule for mongo_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 Mcp Database. Nothing to install.

What risk level is mongo_aggregate? +

mongo_aggregate is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit mongo_aggregate? +

Yes. Add a rate_limit block to the mongo_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.

How do I block mongo_aggregate completely? +

Set action: deny in the PolicyLayer policy for mongo_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.

What MCP server provides mongo_aggregate? +

mongo_aggregate is provided by the Mcp Database MCP server (nam088/mcp-database-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.