The single call an agent makes before transacting with a destination on the open web. Composes the cross-lens verdict with a bounded Tracker-presence bonus, maps the adjusted trust score to a tri-state decision (allow / caution / deny), and returns a 5-minute signed consultation receipt (sigil_to...
Part of the TunnelMind Data API server.
Free to start. No card required.
AI agents call preflight_should_i_act to retrieve information from TunnelMind Data API without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though preflight_should_i_act only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"preflight_should_i_act": {}
}
}See the full TunnelMind Data API policy for all 54 tools.
These attack patterns abuse exactly the kind of access preflight_should_i_act gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
The single call an agent makes before transacting with a destination on the open web. Composes the cross-lens verdict with a bounded Tracker-presence bonus, maps the adjusted trust score to a tri-state decision (allow / caution / deny), and returns a 5-minute signed consultation receipt (sigil_token with sub: preflight:consulted). The receipt is the load-bearing artifact: the agent attaches it to its action log as cryptographic proof that the destination was consulted before action. The decision itself is commodity-shaped; the *receipt of having asked* is what accountability requires. When ait is supplied, the consultation additionally chains a witness-tier preflight:consulted event onto the ATAP AIT, signed by OAI-2026-0000201 — turning the consultation into a hash-chained, replayable artifact. Tracker presence applies a bounded +0.05 trust bonus before decision mapping (capped at 1.0). Absence is never a penalty — most of the open web is not in the tracker corpus and that's expected. Defaults: allow >= 0.70, caution >= 0.40, else deny. Thresholds are overridable per request; weights are inherited from cross_lens_verify.. It is categorised as a Read tool in the TunnelMind Data API MCP Server, which means it retrieves data without modifying state.
Register the TunnelMind Data API MCP server in PolicyLayer and add a rule for preflight_should_i_act: 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 TunnelMind Data API. Nothing to install.
preflight_should_i_act is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the preflight_should_i_act 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 preflight_should_i_act. 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.
preflight_should_i_act is provided by the TunnelMind Data API MCP server (https://mcp-data.tunnelmind.ai/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 TunnelMind Data API 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.