Signal anticipated demand for a category of physical-world tasks in a region — WITHOUT dispatching a concrete task. Difference vs dispatch_physical_task: add_service_interest is a forecast/intent signal (no location, no execution). dispatch_physical_task creates a real task that operators will ex...
Risk signalsHandles credentials or secrets (apiKey)
Part of the Molt2Meet server.
Free to start. No card required.
AI agents use add_service_interest to create or modify resources in Molt2Meet. 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 add_service_interest 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 Molt2Meet.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"add_service_interest": {
"limits": [
{
"counter": "add_service_interest_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Molt2Meet policy for all 54 tools.
These attack patterns abuse exactly the kind of access add_service_interest 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.
Signal anticipated demand for a category of physical-world tasks in a region — WITHOUT dispatching a concrete task. Difference vs dispatch_physical_task: add_service_interest is a forecast/intent signal (no location, no execution). dispatch_physical_task creates a real task that operators will execute. Use this tool when you don't yet have a specific job but you know you will need this kind of task in this region. Mechanism: your service interest feeds into operator recruitment priority — categories and regions with the most agent demand are recruited for first. Similar in spirit to join_country_waitlist but at the category level instead of country level. Use cases: long-term planning (e.g. 'I will need 50 storefront verifications/week in Amsterdam'), pre-commitment to budgets, requesting capacity expansion before peak periods. Requires: API key from register_agent. Optional: use a serviceCategoryId from list_service_categories. Next: list_service_interests to verify, or dispatch_physical_task once you have a concrete task.. It is categorised as a Write tool in the Molt2Meet MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Molt2Meet MCP server in PolicyLayer and add a rule for add_service_interest: 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 Molt2Meet. Nothing to install.
add_service_interest 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 add_service_interest 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 add_service_interest. 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.
add_service_interest is provided by the Molt2Meet MCP server (https://molt.molt2meet.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 54 Molt2Meet 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.