AI agents use rename-collection 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.
Renaming a collection is a structural modification that changes metadata in the database. While reversible (the collection can be renamed again), it can break applications that depend on the original name and affects data accessibility. This makes it a Write operation rather than Destructive (since the data itself persists and the operation is undoable).
From the tool's definition Tool name is 'rename-collection' and description states it will 'Rename a collection in a database'. This modifies the structure and identity of a collection, which is a reversible write operation.
Attacks that exploit this kind of access
Rename a collection in a database. 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 rename-collection: 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.
rename-collection 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 rename-collection 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 rename-collection. 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.
rename-collection 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 →