AI agents use link to create or update resources in Memex — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Memex environment.
Given the server context of a memory/graph system with sibling tools like 'add_node', 'bulk_graph', and 'add_task', 'link' most likely creates a relationship or edge between nodes in the knowledge graph — a reversible write operation. However, the empty description significantly lowers confidence. It cannot be classified as Destructive or Execute without further evidence.
From the tool's definition Tool name is 'link'; description is empty or uninformative.
Attacks that exploit this kind of access
link. It is categorised as a Write tool in the Memex MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Memex MCP server in PolicyLayer and add a rule for 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 Memex. Nothing to install.
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 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 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.
link is provided by the Memex MCP server (queflyhq/memex). 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 →