AI agents use wb_dispute to create or update resources in Workbench — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Workbench environment.
An AI agent can call wb_dispute faster than any human can review — one bad instruction and it creates or modifies resources in Workbench by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
对 approved 内容有实质异议时留痕并停止(等用户裁决,禁止擅自偏离). It is categorised as a Write tool in the Workbench MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Workbench MCP server in PolicyLayer and add a rule for wb_dispute: 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 Workbench. Nothing to install.
wb_dispute 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 wb_dispute 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 wb_dispute. 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.
wb_dispute is provided by the Workbench MCP server (nvrenshiren/workbench). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
wb_dispute is one line of Workbench's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →