Report the dependency impact of an Agda source file. Returns the direct + transitive sets in both directions: which files import this one (dependents) and which files this one imports (dependencies). Use this to pick the most-impactful upstream file to repair first when triaging a multi-file fail...
Risk signalsAccepts file system path (file)
Part of the Agda server.
Free to start. No card required.
AI agents invoke agda_impact to trigger processes or run actions in Agda. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
agda_impact can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"agda_impact": {
"limits": [
{
"counter": "agda_impact_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full Agda policy for all 72 tools.
These attack patterns abuse exactly the kind of access agda_impact gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Report the dependency impact of an Agda source file. Returns the direct + transitive sets in both directions: which files import this one (dependents) and which files this one imports (dependencies). Use this to pick the most-impactful upstream file to repair first when triaging a multi-file failure. Cheap to call repeatedly — the graph is rebuilt from disk each invocation, so newly added files show up without a server restart. Lists are sorted; pass limit to cap each list (default 50, hard cap 500).. It is categorised as a Execute tool in the Agda MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Agda MCP server in PolicyLayer and add a rule for agda_impact: 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 Agda. Nothing to install.
agda_impact is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the agda_impact 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 agda_impact. 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.
agda_impact is provided by the Agda MCP server (agda-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 72 Agda tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.