AI agents call plaid_transactions 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 |
|---|---|---|---|
count | number | — | Number of transactions (max 500, default 100) |
offset | number | — | |
secret | string | Yes | |
end_date | string | Yes | End date (YYYY-MM-DD) |
client_id | string | Yes | |
start_date | string | Yes | Start date (YYYY-MM-DD) |
account_ids | array | — | |
environment | string | — | |
access_token | string | Yes |
Parameters from the server's own tool schema.
This tool retrieves transaction data from Plaid-linked accounts without creating, modifying, or deleting data. It is a Read operation by definition. However, the severity is elevated from 'low' to 'medium' because: (1) transactions reveal sensitive financial information including account activity, amounts, and merchant details; (2) unauthorized exposure could enable identity theft, fraud analysis, or privacy…
From the tool's definition Tool description states 'Get transactions' which is a retrieval operation with no modification capability. Plaid is a financial data aggregation service, making this a financial data read operation.
Risk signalsHandles credentials or secrets (secret)
Attacks that exploit this kind of access
Get transactions for a Plaid-linked item within a date range. It is categorised as a Read tool in the UnClick MCP Server, which means it retrieves data without modifying state.
plaid_transactions accepts 9 parameters: count, offset, secret, end_date, client_id, start_date, account_ids, environment, access_token. Required: secret, end_date, client_id, start_date, 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_transactions: 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_transactions 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_transactions 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_transactions. 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_transactions 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 →