AI agents use add_blocker to create or update resources in Nubis — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nubis environment.
This tool creates or updates task blocking relationships—reversible metadata changes to task records. It affects task workflow status but does not execute external code, delete data irreversibly, or involve financial operations. The medium severity reflects that improper blocking could disrupt project workflows, but the effect is correctable by removing the blocker relationship.
From the tool's definition Tool modifies task state by marking relationships ('Mark a task as blocked by another task'), which is a reversible change to task metadata. Description indicates state modification without deletion or financial impact.
Attacks that exploit this kind of access
Mark a task as blocked by another task. The blocked task cannot be worked on until the blocker is resolved (moved to done). It is categorised as a Write tool in the Nubis MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nubis MCP server in PolicyLayer and add a rule for add_blocker: 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.
add_blocker 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_blocker 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_blocker. 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_blocker 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 →