AI agents use grow_cli_spec to create or update resources in Carrot AI PM — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Carrot AI PM environment.
This tool most likely generates, creates, or modifies CLI specifications as part of a spec-driven development workflow. It does not execute arbitrary code (Execute), delete data (Destructive), move money (Financial), or trigger external operations with unpredictable side effects. The reversible nature of spec generation/modification classifies it as Write.
From the tool's definition Tool name 'grow_cli_spec' suggests it creates or expands a CLI specification. The verb 'grow' in the context of sibling tools like 'grow_db_spec' and 'grow_ui_spec' (which appear to generate or augment specifications) indicates data creation/modification.
Documented attack patterns abuse exactly the kind of access grow_cli_spec gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Carrot AI PM, and nothing reaches the server without passing your rules. This is the rule we recommend for grow_cli_spec:
{
"version": "1",
"default": "deny",
"tools": {
"grow_cli_spec": {
"limits": [
{
"counter": "grow_cli_spec_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}grow_cli_spec 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.
grow_cli_spec. It is categorised as a Write tool in the Carrot AI PM MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Carrot AI PM MCP server in PolicyLayer and add a rule for grow_cli_spec: 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 Carrot AI PM. Nothing to install.
grow_cli_spec 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 grow_cli_spec 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 grow_cli_spec. 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.
grow_cli_spec is provided by the Carrot AI PM MCP server (talvinder/carrot-ai-pm). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 11 Carrot AI PM tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
11 Carrot AI PM tools catalogued and risk-classified — across an index of 42,500+ MCP servers.