AI agents call plaid_accounts to retrieve information from UnClick without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
secret | string | Yes | Plaid secret key |
client_id | string | Yes | Plaid client ID |
account_ids | array | — | Filter to specific account IDs |
environment | string | — | sandbox, development, or production (default: sandbox) |
access_token | string | Yes | Plaid item access token |
Parameters from the server's own tool schema.
This tool retrieves account data from Plaid, which is a read-only operation with no side effects or destructive capability. However, severity is elevated to 'high' because the data accessed is sensitive financial information (bank account details), and unauthorized access or misuse by a compromised agent could enable fraud, identity theft, or privacy violations.
From the tool's definition Tool name 'plaid_accounts' and description 'Get accounts for a Plaid-linked item' indicates a retrieval operation. Plaid is a financial data aggregation service; this tool queries account information without modifying or moving funds.
Risk signalsHandles credentials or secrets (secret)
Attacks that exploit this kind of access
Get accounts for a Plaid-linked item. It is categorised as a Read tool in the UnClick MCP Server, which means it retrieves data without modifying state.
plaid_accounts accepts 5 parameters: secret, client_id, account_ids, environment, access_token. Required: secret, client_id, access_token. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for plaid_accounts: 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 UnClick. Nothing to install.
plaid_accounts is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the plaid_accounts 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_accounts. 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_accounts is provided by the UnClick MCP server (@unclick/mcp-server). 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 →