Reject a HELD acceptance-mode job. Caller gets a full refund and the
AI agents use nexus_reject_job to create or update resources in NexusToken — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your NexusToken environment.
This tool modifies job state (rejection) and triggers a refund, which reverses a financial commitment. While refunds involve money movement, the tool itself is performing a Write operation (state change) rather than directly executing a payment. The financial impact is secondary to the Write action of rejecting/modifying the job record.
From the tool's definition Tool name 'nexus_reject_job' and description stating 'Reject a HELD acceptance-mode job. Caller gets a full refund' indicate state modification of job records and refund processing.
Attacks that exploit this kind of access
Reject a HELD acceptance-mode job. Caller gets a full refund and the. It is categorised as a Write tool in the NexusToken MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the NexusToken MCP server in PolicyLayer and add a rule for nexus_reject_job: 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 NexusToken. Nothing to install.
nexus_reject_job 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 nexus_reject_job 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 nexus_reject_job. 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.
nexus_reject_job is provided by the NexusToken MCP server (bobuilds/nexustoken-sdk). 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 →