Realtime AI News
Meta lets AI coding agents handle WhatsApp Business setup through a new MCP server
Meta introduced a WhatsApp Business Tools MCP server that connects AI coding agents such as Claude, Cursor, Codex and ChatGPT directly to the WhatsApp Business Platform. The server lets an agent create accounts, verify phone numbers, register Cloud API access, build message templates and monitor checks that previously required jumping between Meta's developer tools.
Meta said on Tuesday that it will let businesses point an AI agent of their choosing at WhatsApp Business messaging, so the agent can set up and manage the service on their behalf. The announcement landed alongside news of the company's new AI-focused subscription plans.
The mechanism is a new server called WhatsApp Business Tools MCP. It is built on the Model Context Protocol and wires an AI coding agent, whether Claude, Cursor, Codex or ChatGPT, directly into the WhatsApp Business Platform, so developers can describe what they need in a chat and let the agent carry out the steps.
Meta frames the change as a fix for a clunky process. Onboarding previously meant bouncing between the Developer Console, Meta's Business Manager, the API reference and an editor. Those steps now collapse into a conversation with the agent.
Concretely, the agent can create the company's WhatsApp Business account, add and verify its phone number, register it for Cloud API access and check the business's terms of service. It can also draft a message template from a description, edit an existing template, test messages and webhooks, and monitor items that once failed quietly, including terms of service status, payment method and business verification.
Meta's other server, the Meta Social Technologies MCP, can be used alongside it to discover API endpoints, search documentation and troubleshoot errors during configuration. The launch extends an existing MCP lineup that already covered ad management and app configuration monitoring into the merchant onboarding path.
Opening services to external AI agents through MCP has become common practice. PayPal, Stripe, GitHub, Notion, Slack, Salesforce, Atlassian, X, Google and Microsoft all publish servers that let agents act inside their products. Meta's twist is that the workflow being handed over is the one most likely to need human attention: getting a new merchant live.
For businesses, the promise is a lower technical bar and less manual work. For the platform, it means redrawing permission boundaries, because the agent touches accounts, phone numbers, payment methods and compliance checks. How errors are attributed and how every action is logged will matter as much as the convenience, and it is worth watching whether servers like this become the default way enterprise software exposes itself to agents.
Why it matters
For small merchants the technical bar to messaging on WhatsApp drops sharply, shifting competition toward how capable and reliable an agent is. For platforms and developers, agents now touch accounts, numbers, payments and compliance checks, which makes permission tiers, action logs and human confirmation steps the next requirement rather than a nice-to-have.
Nearby Updates
All09/16, 04:04
VoiceAIWrapper adds a guided AI agent builder to its white-label voice agent platform
VoiceAIWrapper, a white-label AI voice agent platform aimed at agencies, has added a guided AI agent builder, per a press release carried by PRLog. The update shifts voice agent configuration away from custom development and toward a step-by-step setup that agencies can resell.
09/16, 04:27
Exaforce ships an AI security product with a kill switch for rogue agents
Agentic security operations company Exaforce launched Exaforce AI Security, giving security teams visibility into the AI agents running in their environments and the ability to shut down the ones that turn hostile. The release extends a June integration with Anthropic's Claude Compliance API to OpenAI's ChatGPT, Google's Gemini and Microsoft's Copilot.
09/16, 04:40
OpenAI backs a House measure that would require independent audits of AI models
OpenAI has come out in support of a bipartisan House proposal that would require independent audits of AI models, according to CBS News. The endorsement puts a leading lab behind external third-party safety assessments at a moment when the industry's stance on verifiable oversight is shifting.
09/16, 04:47
Spain's data watchdog publicises its first AI agent-linked data breach report
Spain's data protection watchdog has publicised the country's first data breach report tied to an AI agent, saying it received the first notification of a personal data breach allegedly carried out by an artificial intelligence agent. The case pushes autonomous agent behaviour into the regulatory frame, raising immediate questions about attribution, logging and oversight.