Unlink an institution (Plaid item) and delete its local data.
AI agents call remove_institution_tool 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.
Although the server is described as 'read-only' for analysis purposes, this specific tool performs an irreversible destructive action—deleting local data associated with a financial institution. This is a destructive operation because it cannot be undone and results in permanent loss of stored information.
From the tool's definition The tool description states it will 'Unlink an institution (Plaid item) and delete its local data.' The use of 'delete' clearly indicates irreversible removal of data.
Attacks that exploit this kind of access
Unlink an institution (Plaid item) and delete its local data. 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_tool: 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_tool 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_tool 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_tool. 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_tool is provided by the Plaid MCP server (t-rhex/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 →