AI agents use replicate_record to create or update resources in Devon — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Devon environment.
Replicating a record creates a new reference/copy of the record in another group. This is a reversible write operation — the replica can be removed later. It does not delete or overwrite data, execute code, or involve financial operations. The blast radius is medium since an AI agent could create many spurious replicas cluttering the database, but no data is permanently lost.
From the tool's definition Replicate a record within the same database to a destination group
Attacks that exploit this kind of access
Replicate a record within the same database to a destination group. It is categorised as a Write tool in the Devon MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Devon MCP server in PolicyLayer and add a rule for replicate_record: 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 Devon. Nothing to install.
replicate_record 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 replicate_record 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 replicate_record. 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.
replicate_record is provided by the Devon MCP server (mnott/devon). 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 →