Start working on a task. Fetches full task details and checks for blockers. If the task has unresolved blockers, returns an error with blocker IDs. Use this when ready to begin implementation - it provides all context needed and validates the task is ready to work on.
AI agents call work_on_task to retrieve information from Nubis without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool primarily retrieves task details and validates readiness. Despite being named 'work_on_task', the description indicates it fetches information and checks blockers, returning errors for unresolved ones. There is no indication of data modification, execution of code, or destructive actions. It is a read/query operation that prepares context for the user.
From the tool's definition Fetches full task details and checks for blockers... provides all context needed and validates the task is ready to work on
Attacks that exploit this kind of access
Start working on a task. Fetches full task details and checks for blockers. If the task has unresolved blockers, returns an error with blocker IDs. Use this when ready to begin implementation - it provides all context needed and validates the task is ready to work on. It is categorised as a Read tool in the Nubis MCP Server, which means it retrieves data without modifying state.
Register the Nubis MCP server in PolicyLayer and add a rule for work_on_task: 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 Nubis. Nothing to install.
work_on_task 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 work_on_task 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 work_on_task. 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.
work_on_task is provided by the Nubis MCP server (@lil2good/nubis-mcp-server). 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 →