Pause/stop one or more campaigns.
AI agents invoke stop_campaigns to trigger actions in PropellerAds MCP 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 on the PropellerAds advertising platform that halt active campaigns. While not destructive (campaigns can be resumed) or directly financial (no money moves), stopping campaigns is an Execute action because it triggers a state-change operation on external advertising infrastructure whose effects are significant.
From the tool's definition Pauses or stops one or more campaigns, which are active advertising operations with ongoing financial commitments.
Attacks that exploit this kind of access
Pause/stop one or more campaigns. It is categorised as a Execute tool in the PropellerAds MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the PropellerAds MCP Server MCP server in PolicyLayer and add a rule for stop_campaigns: 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 PropellerAds MCP Server. Nothing to install.
stop_campaigns 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_campaigns 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_campaigns. 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_campaigns is provided by the PropellerAds MCP Server MCP server (jannafta/propellerads-mcp). 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 →