AI agents call plaid_get_accounts to retrieve information from VibeServe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves account information from Plaid (a financial data aggregator) without modifying, deleting, or moving money. It is fundamentally a Read operation. However, the severity is elevated to 'high' because the data retrieved—linked financial accounts—is sensitive and could be misused by an agent to identify and target accounts for unauthorized access or information gathering.
From the tool's definition Tool name is 'plaid_get_accounts' and description states 'Get linked Plaid accounts'. The verb 'Get' indicates data retrieval with no modification. Plaid is a financial data aggregation service, making the retrieved accounts sensitive financial information.
Attacks that exploit this kind of access
Get linked Plaid accounts. It is categorised as a Read tool in the VibeServe MCP Server, which means it retrieves data without modifying state.
Register the VibeServe MCP server in PolicyLayer and add a rule for plaid_get_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 VibeServe. Nothing to install.
plaid_get_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_get_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_get_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_get_accounts is provided by the VibeServe MCP server (ncsound919/vibeserve). 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 →