Creates flagpost.config.ts in a project directory. Scaffolds a starter config with an example feature flag.
AI agents use flagpost_init to create or update resources in Clocktower — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Clocktower environment.
This tool creates a new configuration file in the project directory. It is a write operation (file creation) but not destructive since it scaffolds a new file rather than overwriting existing data. The blast radius is low as it only creates a starter config file with an example feature flag.
From the tool's definition Creates flagpost.config.ts in a project directory. Scaffolds a starter config with an example feature flag.
Documented attack patterns abuse exactly the kind of access flagpost_init gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Clocktower, and nothing reaches the server without passing your rules. This is the rule we recommend for flagpost_init:
{
"version": "1",
"default": "deny",
"tools": {
"flagpost_init": {
"limits": [
{
"counter": "flagpost_init_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}flagpost_init stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Creates flagpost.config.ts in a project directory. Scaffolds a starter config with an example feature flag. It is categorised as a Write tool in the Clocktower MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Clocktower MCP server in PolicyLayer and add a rule for flagpost_init: 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 Clocktower. Nothing to install.
flagpost_init 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 flagpost_init 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 flagpost_init. 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.
flagpost_init is provided by the Clocktower MCP server (sathergate/sathergate-toolkit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Clocktower, 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.
26 Clocktower tools catalogued and risk-classified — across an index of 43,000+ MCP servers.