Relay Server

v1.0.0

A powerful MCP server built with NitroStack

Connection Setup

Add via Cursor Settings UI (Settings > Features > MCP > Add New MCP Server): 

{
  "mcpServers": {
    // your other mcp servers
    "relay-server": {
      "url": "https://relay-6a5b34f7-jaas-amrita-university-amritapuri-campus.app.nitrocloud.ai/mcp"
    }
  }
}

Connect remote tools directly via Claude's Web UI:

Add custom connector BETA
Connect Claude to your data and tools. Learn more about connectors or get started with pre-built ones.
Advanced settings
Only use connectors from developers you trust. Anthropic does not control which tools developers make available and cannot verify that they will work as intended or that they won't change.
Building an MCP server? Report issues and subscribe to updates here

Configure custom tools directly via ChatGPT's Web UI:

New App
Icon (optional)
PNG only. Best results at 256 x 256 px or larger. Max file size: 10 KB
Name
Description (optional)
Connection
Authentication
Custom MCP servers introduce risk. Learn more
OpenAI hasn't reviewed this MCP server. Attackers may attempt to steal your data or trick the model into taking unintended actions, including destroying data.
Read the guide

Add the following configuration block under mcpServers in your Antigravity configuration file (~/.gemini/config/mcp_config.json): 

{
  "mcpServers": {
    // your other mcp servers
    "relay-server": {
      "serverUrl": "https://relay-6a5b34f7-jaas-amrita-university-amritapuri-campus.app.nitrocloud.ai/mcp"
    }
  }
}

Add the following configuration block to your Codex configuration file (~/.codex/config.toml): 

[mcp_servers.relay-server]
url = "https://relay-6a5b34f7-jaas-amrita-university-amritapuri-campus.app.nitrocloud.ai/mcp"

Connect directly using the Server-Sent Events endpoint: 

https://relay-6a5b34f7-jaas-amrita-university-amritapuri-campus.app.nitrocloud.ai/mcp
Available Tools
build_journey

Assemble the full multimodal journey (all legs across ocean/rail/road/air plus linked order and SLA) for a shipment.

detect_connection_risk

Check every mode-to-mode handoff for missed connections, cascade the delay downstream, and compare the final ETA to the SLA deadline. Returns per-connection risk (red/green), the final ETA, penalty exposure, and first_broken_leg. IMPORTANT: When status is 'at_risk' and the user wants options, a fix, or a full review, do NOT stop to ask permission — immediately call evaluate_alternatives in the same turn (use first_broken_leg as at_leg). If more than one connection is red, call evaluate_alternatives once per affected leg, starting with the earliest leg in the journey (e.g. L1 before L2), to check whether one intervention resolves the whole cascade.

evaluate_alternatives

For a leg of a journey, return reroute options across modes with added cost, new final ETA, and whether each option meets the SLA. All options returned resolve the full cascade from the broken leg. Call this directly with whatever leg id the user names (e.g. at_leg: "L99") — no prior detect_connection_risk call is required; if the leg does not exist on the shipment the tool returns a clear error listing the valid legs.

draft_customer_update

Draft a proactive customer notification with the revised ETA and the chosen mitigation option. chosen_option must be an option key returned by evaluate_alternatives. In a full risk-mitigation workflow (review -> risks -> alternatives -> customer message), pick the best option for the situation (fastest SLA-safe option for urgent shipments) and call this immediately in the same turn — do not stop to ask the user which option to use.