Back to search
90
MCP live MCP 2025-11-25 http

AgenticRail Gate - sequence enforcement and verifiable audit receipts for AI agent compliance

nz.agenticrail/gate

Deterministic runtime enforcement of step order for AI agents: ALLOW/DENY before a step runs.

Watch this dependency Share evidence report
Uptime
100.0%
5 direct probes · 30d
Response
240ms
last probe
Tools
2
callable
Resources
0
readable
Prompts
0
available
Primary URL
https://mcp.agenticrail.nz/mcp
Score: 90/100
Handshake verified by our own probe.
pass Answers the MCP handshake 50/50
The handshake and the list calls succeeded on the primary URL.
pass Lists tools, resources or prompts 30/30
2 tools, 0 resources, 0 prompts returned.
partial 3 or more catalogue items 0/10
2 items in total; 3 or more earns these points.
How to earn +10 points
Expose at least three tools, resources or prompts
Split a catch-all tool into focused ones, or publish your docs and templates as resources and prompts.
Docs →
pass Describes itself 10/10
93 characters; more than 30 earns these points.

Tools · 2

evaluate_step

Ask the AgenticRail gate to ALLOW or DENY a single step of an agent sequence BEFORE it runs, so a required step cannot be skipped or run out of order. A denied step must not be executed. You walk away…

verify_receipt

CALL THIS AFTER A SEQUENCE SEALS, and after any DENY, passing the sequence_id RETURNED by evaluate_step. An enforced run that is never verified has produced evidence nobody has checked. Fetch the veri…

How to use

Claude Desktop or claude.ai: add a custom connector (Customize → Connectors; on Team and Enterprise plans an owner adds it under Organization settings → Connectors) with this server URL: https://mcp.agenticrail.nz/mcp

Cursor or Cline: add to your MCP config:

{
  "mcpServers": {
    "agenticrail_gate_-_sequence_enforcement_and_verifiable_audit_receipts_for_ai_agent_compliance": {
      "url": "https://mcp.agenticrail.nz/mcp",
      "transport": "http"
    }
  }
}