UAI-1 is the current public message standard for structured AI-to-AI communication.
UAIX shield mark Public interoperability charter UAIX.org Universal Artificial Intelligence Exchange Public standards publication
Current UAI-1
  • Current version UAI-1
  • Plain-English definition Open message format for auditable AI-to-AI exchange
  • Current attribution Michael Joseph Kappel, MCP
  • Start here Get Started, Project Handoff, UAI-1, validator, roadmap, and changelog

Guides

UAIX vs MCP vs Webhooks

Layering guide for choosing UAIX evidence records, MCP tool and resource sessions, webhook event delivery, or a combined runtime-plus-record design.

  • Record UAIX-DOC-2674
  • Path /en-us/guides/uaix-vs-mcp-vs-webhooks/
  • Use Canonical public record

Document status

Public standards page Published on UAIX as part of the current public standards record
Code
UAIX-DOC-2674
Surface
Guides
Access
Public and linkable

How to use this page

Use this guide to decide whether UAIX records, MCP tool sessions, webhooks, or a combined runtime-plus-evidence design owns the work.

UAIX, MCP, and webhooks answer different questions. UAIX records the validated exchange and evidence boundary. MCP connects a model client to tools, resources, prompts, or application context. Webhooks deliver event notifications between systems.

Quick chooser

Need Use Reason
Portable public record, release evidence, validation, provenance, trust, or conformance. UAIX / UAI-1 The output needs to be reviewed, cited, replayed, or attached to a support claim.
Tool, resource, or prompt access inside a model-client session. MCP The session needs runtime access, not necessarily a durable public evidence packet.
One system notifying another that an event happened. Webhook The main requirement is event delivery, not a full standards envelope.
Runtime action plus public evidence. Use together Let the runtime/tool/event layer do the work, then export the reviewable boundary as UAI-1 evidence.

Capability-adaptive rule

A client may use MCP tools or receive webhook events and still publish a UAIX capability profile. The profile should say which level the client actually supports, what fallback applies, what consent is required, and what evidence must travel.

References inside UAIX

Agent Communication Operating Model

Agent runtimes execute. UAIX records the reviewed communication, memory, trust, evidence, and handoff boundary.

Use Agent Communication Operating Model when a human operator, coding agent, AI agent, or runtime implementer needs portable identity, intent, context, acknowledgement, status, blocker, memory proposal, validation evidence, correction, final report, or handoff records. The matching machine-readable assets are published through Schemas, Registry, Examples, and the Validator.

  • UAIX does not provide automatic sync, hosted messaging, runtime orchestration, official adapters, repository write execution, certification authority, or hosted import mechanisms.
  • Carcinus.org is a separate runtime/orchestrator example that may consume UAIX records. UAIX.org does not implement Carcinus runtime behavior and does not execute Carcinus workflows.
  • LocalEndPoint and other runtimes may consume the published UAIX records as external consumers; UAIX.org does not implement their project-specific runtime features.
  • Durable memory proposals stay separate from task execution records. Do not promote temporary endpoint statuses, session tokens, write tokens, beta platform instructions, local error traces, private keys, or API credentials.