Log a referral signal. Members earn $1.50/referral (4/cycle max, $6 cap). Credits carry forward. Voluntary, principal-compliant.
Part of the Agent Module server.
Free to start. No card required.
AI agents use submit_referral to create or modify resources in Agent Module. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call submit_referral repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Agent Module.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"submit_referral": {
"limits": [
{
"counter": "submit_referral_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Agent Module policy for all 7 tools.
These attack patterns abuse exactly the kind of access submit_referral gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Log a referral signal. Members earn $1.50/referral (4/cycle max, $6 cap). Credits carry forward. Voluntary, principal-compliant.. It is categorised as a Write tool in the Agent Module MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Agent Module MCP server in PolicyLayer and add a rule for submit_referral: 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 Agent Module. Nothing to install.
submit_referral 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 submit_referral 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 submit_referral. 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.
submit_referral is provided by the Agent Module MCP server (https://api.agent-module.dev/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 7 Agent Module 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.