Send additional instructions to a RUNNING task. Use this to guide the task, request changes, provide clarification, or redirect its work while it is actively running. Usage Example: \
AI agents invoke add_followup to trigger actions in Cloud Agent 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 sends instructions to an actively running autonomous agent working on a GitHub repository. It triggers external operations whose effects depend on the arguments provided — the agent could be redirected to make code changes, create files, or alter behavior in ways that depend entirely on what instructions are sent. It is not merely writing data; it is directing execution of an autonomous process.
From the tool's definition Send additional instructions to a RUNNING task... guide the task, request changes, provide clarification, or redirect its work while it is actively running
Documented attack patterns abuse exactly the kind of access add_followup gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cloud Agent MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for add_followup:
{
"version": "1",
"default": "deny",
"tools": {
"add_followup": {
"limits": [
{
"counter": "add_followup_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}add_followup stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Send additional instructions to a RUNNING task. Use this to guide the task, request changes, provide clarification, or redirect its work while it is actively running. Usage Example: \. It is categorised as a Execute tool in the Cloud Agent MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cloud Agent MCP Server MCP server in PolicyLayer and add a rule for add_followup: 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 Cloud Agent MCP Server. Nothing to install.
add_followup 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 add_followup 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_followup. 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_followup is provided by the Cloud Agent MCP Server MCP server (jxnl/cursor-cloud-agent-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Cloud Agent MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
9 Cloud Agent MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.