AI agents use grow_db_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.
Without an explicit description, classification relies on the naming pattern and server context. The 'grow_*' family of tools on this spec-driven development platform appears to generate or extend specifications (Write category: creates/modifies data reversibly). Database specs are configuration artifacts that can be modified but are not destructive in nature.
From the tool's definition Tool name 'grow_db_spec' suggests generating or expanding a database specification. In the context of a spec-driven development tool, 'grow' typically means creating or modifying spec artifacts.
Documented attack patterns abuse exactly the kind of access grow_db_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_db_spec:
{
"version": "1",
"default": "deny",
"tools": {
"grow_db_spec": {
"limits": [
{
"counter": "grow_db_spec_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}grow_db_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_db_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_db_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_db_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_db_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_db_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_db_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.