Skip to Content
Platform Ontology

Page tools for AI agents (WebMCP)

A page can list actions an AI agent in the browser may call, instead of the agent guessing at buttons.

While you use it

WebMCP is a proposed web standard. A page registers named tools with a description and input schema through navigator.modelContext, or marks up forms. A browser agent can then call a tool such as search flights or add to cart directly. It is an early preview in Chrome behind a flag and may change.

What it can and can't do

What the user does: None for the page owner. Agents or browsers may ask you before they call a tool

It can

  • Expose named actions with typed inputs
  • Let an agent skip fragile clicking
  • Keep your own checks and limits in your tool code
  • Work next to the normal page for people

It cannot

  • Run without a browser agent present
  • Stop an agent from using the visible page
  • Prove who the agent is
  • Ship to all browsers today

How it differs between platforms: Only Chrome has an early preview, behind a flag. Names, shapes and permission rules can still change.

Browser support

Version notes
  • Chrome: Early preview behind a flag; may change
  • Edge: No public status found
  • Firefox: No public status found
  • Safari: No public status found

How a site asks for it

APInavigator.modelContext.registerTool({name, description, inputSchema, execute}); declarative form attributes
How access is grantednone
What the user seesNone defined yet in the draft
Needs a secure context (HTTPS)Yes
Needs a user gestureNo
How long it lastsTools live while the page is open
How to take it backClose the page or unregister the tool
Inside an iframeDraft rules for frames are not settled

Typical flow

  1. Page registers tools with names and input schemas
  2. An agent in the browser reads the tool list
  3. The agent calls a tool; the page code runs it
  4. Browser rules for who may call tools are still being drafted

Data you get

Shape: object
How often: set by the page

FieldTypeUnitRangePrecision
namestringNonetool nameNot listed
descriptionstringNonewhat the tool does, read by the agentNot listed
inputSchemaobjectNoneJSON Schema for the argumentsNot listed
executefunctionNonepage code that runs when the agent calls the toolNot listed

Technical limits

  • Early preview only
  • Permission model not final
  • Not identity; says nothing about who the agent is

The story

What it is

A site tells agents what they can do, in a menu, rather than letting them poke at the screen.

For you

You will not see it. If you use a browser agent, the sites it visits may offer tools so the agent works faster and makes fewer mistakes.

For makers

Validate every argument in your tool code and apply the same rules as for a user. Do not treat an agent call as safe. Plan for the spec to change.

Where you see it

TypeExampleApps
shoppingA store exposes add to cart and check stock as tools.None named
travelA travel site exposes a search flights tool that returns structured results.None named
productivityA task app exposes create task and list tasks.None named
developerA team tests how agents use their tools in Chrome with the flag on.Chrome
enterpriseAn internal portal publishes approved actions for staff agents.None named
accessibilityClear tool names help agents act for people who cannot use a mouse.None named

Risks

  • Prompt injection through tool descriptions
  • Agents acting without a clear person's yes
  • Preview may change

What the platform says

Good uses and abuse

Legitimate uses

  • Agent friendly sites
  • Faster, safer agent actions than clicking

Known abuse

  • Prompt injection
  • Agents doing more than the person meant

Scores

ScoreValueMeaning
Sensitivity3 of 5How revealing the data is
Utility4 of 5How useful it is to honest apps
Friction1 of 5How much the user has to do
Fingerprint bits0.1Rough identifying entropy, when known

History

  • 2026-02, Chrome 146: WebMCP early preview in Chrome behind a flag

Sources

How well checked: Inferred from related behavior.

On this page