AI agents use update-many to create or update resources in Mongodb3 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mongodb3 environment.
This tool modifies data in MongoDB by updating multiple documents that match specified filter conditions. While updates are reversible (unlike deletions), the ability to modify many documents at once with a single operation creates significant risk if misused by an agent.
From the tool's definition Tool name 'update-many' and description 'Update all documents matching a filter' indicate bulk modification of data. The function updates multiple documents based on filter criteria, which is a reversible write operation.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Update all documents matching a filter. It is categorised as a Write tool in the Mongodb3 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mongodb3 MCP server in PolicyLayer and add a rule for update-many: 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 Mongodb3. Nothing to install.
update-many 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-many 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-many. 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-many is provided by the Mongodb3 MCP server (mongodb3-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 →