plaid_unlink
AI agents call plaid_unlink to permanently remove resources in Plaid — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The name 'plaid_unlink' strongly implies it removes or disconnects a linked financial account from Plaid. Unlinking a financial account is likely irreversible in the sense that it would remove the connection and potentially delete associated tokens/credentials, requiring re-linking to restore. This is most analogous to a Destructive action (removing an established connection/data).
From the tool's definition Tool name 'plaid_unlink' on a server with sibling tools including 'plaid_link' and 'plaid_relink'; empty description.
Attacks that exploit this kind of access
plaid_unlink. It is categorised as a Destructive tool in the Plaid MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Plaid MCP server in PolicyLayer and add a rule for plaid_unlink: 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 Plaid. Nothing to install.
plaid_unlink is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the plaid_unlink 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 plaid_unlink. 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.
plaid_unlink is provided by the Plaid MCP server (yuechen/plaid-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 →