Model Context Protocol
MCP for logistics: letting AI assistants call a real optimizer
MCP is an open standard that lets AI assistants use external tools securely. For logistics, it is the difference between an assistant that describes route planning and one that can actually run it.
What is MCP?
The Model Context Protocol defines how an AI client, such as Claude or ChatGPT, discovers and calls tools exposed by a server. Each tool has a name, a typed set of parameters and a structured result.
Authorization follows OAuth, so the assistant acts with permissions you grant and can revoke.
Why it matters for logistics teams
- Dispatchers can work in plain language instead of learning another interface.
- Results come from tested software, not from a model's guess.
- Sensitive customer data stays in the platform, not in the chat.
- The same tools work across compatible AI assistants.
The AIRO tool set
- create_import: start an import and get a secure upload link
- validate_import and update_import_mapping: check and fix the data
- create_optimization_job and get_job_status: run and monitor a plan
- get_optimization_result: KPIs, route summary, unassigned orders
- compare_scenarios: baseline vs. optimized
- export_result: Excel or CSV for drivers
Safety by design
Every call is authenticated, scoped to a company, rate limited and logged. Mutations are idempotent so a repeated request cannot create duplicate jobs or duplicate billing. The assistant never receives the full uploaded file.
Frequently asked questions
What is MCP?
MCP (Model Context Protocol) is an open standard that lets AI assistants call external tools securely. In AIRO, MCP exposes actions like "validate import" and "optimize routes" to Claude or ChatGPT. The assistant is the interface; the AIRO backend does the work.
Does AIRO work with Claude?
Yes. AIRO is designed to connect to Claude through MCP (Model Context Protocol). Once connected, you can ask Claude to validate an import, launch an optimization, compare scenarios or export driver sheets. Claude calls the AIRO engine, which performs the optimization.
Does AIRO work with ChatGPT?
AIRO is built on MCP, an open standard that ChatGPT and other AI clients are adopting. Availability of MCP connectors inside ChatGPT depends on your OpenAI plan and OpenAI's current rollout. The full browser portal works regardless of which assistant you use.
Is my customer address data used to train AI models?
No. Customer files are processed by the AIRO optimization engine, not used as training data. The full contents of your uploaded file are never sent to an LLM. When you use an AI assistant, it only receives summaries and results returned by the platform's tools.
Join the waitlist
Get early access and launch updates. Double opt-in, unsubscribe anytime.