AI agents use create_tool_policy to create or update resources in Pypi:asqav — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pypi:asqav environment.
The tool creates (writes) policy rules that modify the governance state of the system. While this is reversible via 'delete_tool_policy', it affects authorization boundaries and agent capabilities system-wide, making it Write with high severity. Not Destructive because policies can be deleted; not Execute because it doesn't directly run operations (it configures controls).
From the tool's definition Tool named 'create_tool_policy' on a governance/policy enforcement server; sibling tools include 'delete_tool_policy', 'list_tool_policies', and 'enforced_tool_call', establishing a clear policy management context.
Documented attack patterns abuse exactly the kind of access create_tool_policy gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pypi:asqav, and nothing reaches the server without passing your rules. This is the rule we recommend for create_tool_policy:
{
"version": "1",
"default": "deny",
"tools": {
"create_tool_policy": {
"limits": [
{
"counter": "create_tool_policy_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_tool_policy 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.
create_tool_policy. It is categorised as a Write tool in the Pypi:asqav MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pypi:asqav MCP server in PolicyLayer and add a rule for create_tool_policy: 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 Pypi:asqav. Nothing to install.
create_tool_policy 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 create_tool_policy 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 create_tool_policy. 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.
create_tool_policy is provided by the Pypi:asqav MCP server (jagmarques/asqav-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Pypi:asqav, 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.
15 Pypi:asqav tools catalogued and risk-classified — across an index of 43,000+ MCP servers.