Stops a running background task by its name.
AI agents invoke stop-background-task to trigger actions in MCP Background Task Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers external operations (process termination) whose effects cannot be trivially undone—a running build or development server interrupted mid-task could leave systems in inconsistent states, disrupt deployments, or cause client disconnects. It is more severe than Write (which creates/modifies reversibly) but falls short of Destructive (which targets data) or Financial.
From the tool's definition The tool 'stops a running background task by its name' performs a control-plane action that terminates a process.
Attacks that exploit this kind of access
Stops a running background task by its name. It is categorised as a Execute tool in the MCP Background Task Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Background Task Server MCP server in PolicyLayer and add a rule for stop-background-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 MCP Background Task Server. Nothing to install.
stop-background-task is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the stop-background-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 stop-background-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.
stop-background-task is provided by the MCP Background Task Server MCP server (nanoseil/mcp-bgtask). 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 →