Auto-generate .astrographignore with reasonable defaults for excluding files from indexing.
AI agents use generate_ignore to create or update resources in Astrograph — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Astrograph environment.
This tool writes a new configuration file (.astrographignore) to the filesystem. While it creates a file, the operation is reversible (the file can be deleted or edited), and the impact is limited to configuration of the duplicate-code detection system itself.
From the tool's definition Tool creates or modifies a .astrographignore configuration file with default exclusion patterns. Description states 'Auto-generate .astrographignore' which is a file creation/modification operation.
Documented attack patterns abuse exactly the kind of access generate_ignore gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Astrograph, and nothing reaches the server without passing your rules. This is the rule we recommend for generate_ignore:
{
"version": "1",
"default": "deny",
"tools": {
"generate_ignore": {
"limits": [
{
"counter": "generate_ignore_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}generate_ignore 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.
Auto-generate .astrographignore with reasonable defaults for excluding files from indexing. It is categorised as a Write tool in the Astrograph MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Astrograph MCP server in PolicyLayer and add a rule for generate_ignore: 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 Astrograph. Nothing to install.
generate_ignore 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 generate_ignore 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 generate_ignore. 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.
generate_ignore is provided by the Astrograph MCP server (thaylo/astrograph). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Astrograph, 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.
12 Astrograph tools catalogued and risk-classified — across an index of 43,000+ MCP servers.