AI agents use migrate_to_project to create or update resources in Engram — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Engram environment.
This tool creates or modifies data by reassigning memories between projects. While it doesn't delete data, it irreversibly changes where memories are stored/grouped within the system. It's Write rather than Destructive because the data itself persists—only its organizational location changes.
From the tool's definition Tool description states 'Mueve memorias' (moves memories) from a source project to a destination project based on a tag. This is a data migration operation that modifies the project assignment of memories.
Attacks that exploit this kind of access
Mueve memorias que contengan un tag específico desde un proyecto origen a un proyecto destino. It is categorised as a Write tool in the Engram MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Engram MCP server in PolicyLayer and add a rule for migrate_to_project: 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 Engram. Nothing to install.
migrate_to_project 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 migrate_to_project 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 migrate_to_project. 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.
migrate_to_project is provided by the Engram MCP server (jacksini/engram-mcp). 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 →