Platform

What is WebMCP?

WebMCP is a proposed browser interface through which a web page exposes structured tools that agents can invoke.

The WebMCP draft dated September 4, 2026 is a Community Group report. Its publisher is the Web Machine Learning Community Group at W3C, the web standards organization. That draft is neither a W3C Standard nor a Standards Track specification.

The proposal lets a website describe actions directly to an agent. That gives the agent another way to interact alongside the page's visible controls.

What does a page expose?

A page exposes named tools with descriptions and structured inputs. Its application code implements the requested behavior.

The WebMCP draft describes JavaScript tools and a declarative form interface. A tool can describe an operation that otherwise requires the agent to infer how to use the page.

For example, an appointment page could expose a search operation with location and date inputs. The agent supplies those values instead of reconstructing the search from labels and controls.

How is this different from a remote MCP server?

WebMCP exposes functionality from a running web page. A remote MCP integration connects a client to a server outside that page.

The WebMCP explainer describes the distinction in terms of shared browser context. Page tools can reuse the web application's code. They can participate in a workflow the user can see.

A backend integration instead connects the agent's application to a service endpoint. The service can expose operations independently of a particular open page.

IntegrationWhere the capability is exposedExample
WebMCPA running web pageSearch appointments using the page's application code
Remote MCPA server endpointInvoke a messaging operation through a connected client

A site can use both approaches. A page tool may call a backend, so browser exposure does not mean every action happens locally.

Does a tool description make an action safe?

A description tells the agent what a tool claims to do. The application still needs to enforce permissions and validate the request.

The draft's security and privacy considerations address misleading tool metadata, injected instructions and unintended actions. Structured inputs do not establish that a requested action matches the user's intent.

For a booking workflow, finding available appointments and confirming a booking have different consequences. The application should preserve that distinction when it exposes tools.

A publisher's tool registration also does not establish that every browser can invoke it. Chrome's WebMCP documentation describes its own implementation and limitations.

How do I connect an agent to Bird for messaging?

You can connect a compatible client to Bird's hosted MCP server and complete the browser sign-in.

That is a remote MCP connection. It gives the client access to Bird's documented tool interface rather than declaring tools in an open Bird web page.

After sending, retain the message identifier and check its later status. The existing MCP answer covers the connection and messaging workflow.

Développez sur le même réseau.

Une clé API de test est disponible immédiatement. La production est activée dès que vous ajoutez un moyen de paiement et vérifiez un expéditeur.

Commencez avec un seul canal.
Ajoutez les autres quand vous êtes prêt.

Une clé API de test est disponible immédiatement. L'accès production se débloque dès que vous ajoutez un moyen de paiement et vérifiez un expéditeur.

Vous utilisez Claude Code, Cursor ou Codex ? Copiez un prompt de configuration et votre agent installe la CLI Bird et les compétences pour vous. Choisissez le vôtre :

Cursor