Creates a directional relationship link between two Engrams items (e.g., a decision
AI agents use link_engrams_items to create or update resources in Engrams — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Engrams environment.
This tool creates a new relationship/link between existing items. It is a write operation that modifies the data model by establishing associations, but does not delete or irreversibly destroy data. Misuse could corrupt the knowledge graph structure, warranting medium severity.
From the tool's definition Creates a directional relationship link between two Engrams items
Documented attack patterns abuse exactly the kind of access link_engrams_items gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Engrams, and nothing reaches the server without passing your rules. This is the rule we recommend for link_engrams_items:
{
"version": "1",
"default": "deny",
"tools": {
"link_engrams_items": {
"limits": [
{
"counter": "link_engrams_items_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}link_engrams_items stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Creates a directional relationship link between two Engrams items (e.g., a decision. It is categorised as a Write tool in the Engrams MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Engrams MCP server in PolicyLayer and add a rule for link_engrams_items: 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 Engrams. Nothing to install.
link_engrams_items 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 link_engrams_items 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 link_engrams_items. 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.
link_engrams_items is provided by the Engrams MCP server (stevebrownlee/engrams). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Engrams, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
42 Engrams tools catalogued and risk-classified — across an index of 43,000+ MCP servers.