Neurotwin Evolver

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
    "neurotwin-evolver": {
      "url": "https://team-knights-6a64deca-team-knights-amrita-university-coimbatore.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
    "neurotwin-evolver": {
      "serverUrl": "https://team-knights-6a64deca-team-knights-amrita-university-coimbatore.app.nitrocloud.ai/mcp"
    }
  }
}

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

[mcp_servers.neurotwin-evolver]
url = "https://team-knights-6a64deca-team-knights-amrita-university-coimbatore.app.nitrocloud.ai/mcp"

Connect directly using the Server-Sent Events endpoint: 

https://team-knights-6a64deca-team-knights-amrita-university-coimbatore.app.nitrocloud.ai/mcp
Available Tools
view_fleet_twin

Display the live NeuroTwin digital-twin map of the fleet - UAVs, AGVs, conveyor cells, battery racks and safety gates - with real-time status, battery, and throughput across logistics, manufacturing, energy, and safety domains.

monitor_environmental_shifts

List environmental shifts the agent has detected (weather, regulatory, hardware, market) that its original training did not anticipate, and their current mutation/resolution status.

run_mutation_cycle

Runs a Safe Test-Driven Mutation Cycle for a detected environmental shift: generates several candidate logic variants, simulates each in the NeuroTwin digital twin, scores them on fitness, energy delta, and safety margin, then deploys the fittest one to the affected units. Also runs the 5-agent validation pipeline (ResourceManager -> LogicRefactor -> Validator -> EthicalGuardrail) per affected unit.

get_unit_detail

Display detailed telemetry and mutation history for a single fleet unit, including its current status, battery, throughput, domain, and the last logic mutation deployed to it.

check_swarm_comms

Evaluates communication health across the fleet swarm and decides whether the Protocol-Evolver agent should switch topology (leader-follower / mesh / cellular) to route around degraded nodes. Returns null topologyDecision if the swarm is healthy and no change is needed.

inject_environmental_shift

Manually reports a new environmental shift for the swarm to react to (for demo/testing). Adds it to the active shift list so evolve_logic or run_mutation_cycle can then resolve it.

evolve_logic

Runs the full autonomous logic-evolution loop for an environmental shift as a long-running operation: generates candidate logic variants, simulates each in the NeuroTwin digital twin, and deploys the fittest one. Pass `task: {}` to run it asynchronously and poll progress.

self_heal_unit

Proactively heals a degraded fleet unit by rerouting its operational logic (e.g. falling back to a nearby stationary sensor when onboard hardware fails). REQUIRES task augmentation - pass `task: {}`.