AI agents use update_link 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 reverses a data modification within the structured memory graph—updating relationship types between nodes. While it does not delete or irreversibly destroy data, it alters the stored relationships, making it a Write rather than Read operation.
From the tool's definition update_link modifies 'el tipo de relación de un enlace ya existente' (the relationship type of an existing link). This is a modification operation applied to a graph structure within the memory database.
Attacks that exploit this kind of access
Actualiza el tipo de relación de un enlace ya existente entre dos memorias. 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 update_link: 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.
update_link 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_link 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_link. 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_link 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 →