AI agents use update to create or update resources in MongoDB — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MongoDB environment.
The tool modifies data in MongoDB collections. Updates are reversible (documents can be updated again or rolled back), so this is Write rather than Destructive. The severity is medium because unintended updates could corrupt application data, but the damage is not permanent and can be recovered.
From the tool's definition Tool name is 'update' and description states 'Update documents in a MongoDB collection'. The server description emphasizes 'read-only queries', but this tool explicitly performs document updates, which is a reversible write operation.
Documented attack patterns abuse exactly the kind of access update gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MongoDB, and nothing reaches the server without passing your rules. This is the rule we recommend for update:
{
"version": "1",
"default": "deny",
"tools": {
"update": {
"limits": [
{
"counter": "update_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Update documents in a MongoDB collection. It is categorised as a Write tool in the MongoDB MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MongoDB MCP server in PolicyLayer and add a rule for update: 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. Nothing to install.
update is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update 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 update. 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.
update is provided by the MongoDB MCP server (kiliczsh/mcp-mongo-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MongoDB, 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.
8 MongoDB tools catalogued and risk-classified — across an index of 43,000+ MCP servers.