Compensate a saga step (refund vault -> payer). With cascade=True, also
AI agents use workflow_step_compensate to commit financial operations through Tenzro Ledger MCP — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool performs a financial refund operation, moving funds from a vault back to a payer. This is a financial transaction that reverses a payment step in a saga workflow. Given the server context (wallet, payments, staking, bridges) and the vault-to-payer fund movement, this is clearly a Financial category tool.
From the tool's definition Compensate a saga step (refund vault -> payer)
Attacks that exploit this kind of access
Compensate a saga step (refund vault -> payer). With cascade=True, also. It is categorised as a Financial tool in the Tenzro Ledger MCP MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Tenzro Ledger MCP server in PolicyLayer and add a rule for workflow_step_compensate: 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 Tenzro Ledger MCP. Nothing to install.
workflow_step_compensate is a Financial 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 workflow_step_compensate 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 workflow_step_compensate. 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.
workflow_step_compensate is provided by the Tenzro Ledger MCP server (https://canton-mcp.tenzro.network/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 →