AI agents use add_external_debt_tool to create or update resources in Plaid — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Plaid environment.
This tool creates or modifies debt tracking data by adding external debt entries to the user's financial profile. While the server is described as 'read-only' for Plaid-linked accounts, this specific tool performs a write operation (adding/creating new debt records).
From the tool's definition Tool description states 'Track a debt that isn't behind a linked Plaid account.' The verb 'track' combined with adding external debt indicates data creation/modification.
Attacks that exploit this kind of access
Track a debt that isn't behind a linked Plaid account. It is categorised as a Write tool in the Plaid MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Plaid MCP server in PolicyLayer and add a rule for add_external_debt_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.
add_external_debt_tool is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_external_debt_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 add_external_debt_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.
add_external_debt_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 →