Revokes the access token at Plaid and deletes the local record.
AI agents call remove_institution 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.
This tool permanently removes a linked financial institution connection and deletes associated local records. The action cannot be undone without re-linking the institution. While not directly moving money, it represents destructive modification of persistent state in a financial context.
From the tool's definition Tool description states 'deletes the local record' and 'revokes the access token', indicating irreversible removal of authentication and stored data.
Attacks that exploit this kind of access
Revokes the access token at Plaid and deletes the local record. 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 remove_institution: 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.
remove_institution 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 remove_institution 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 remove_institution. 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.
remove_institution is provided by the Plaid MCP server (wilderfield/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 →