Matterport for AI agents

Matterport creates immersive 3D tours of physical spaces, used here to manage and share captured 3D models with clients and prospective buyers. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Design and imagesOAuth 2.0MCP + RESTmatterport.com
AUDIT LOG · MATTERPORTPOLICY: acme-support
09:41:09 · claude · u_8f2write
matterport.update_model_state
Update Model State✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
matterport.delete_model
Delete Matterport Model✕ blocked · policy: deny
EVERY MATTERPORT CALL, ON THE RECORD
01 · USE CASES

What agents do in Matterport.

01

Look up a 3D model's details

Check a captured model's metadata and status before sharing it with a client, read-only.

02

List room classifications

Pull the detected room types in a model to verify a space was scanned correctly.

03

Approve before deleting a model

Require approval before deleting a 3D model, since it removes the entire captured tour.

02 · ACTIONS

6 Matterport actions, graded by risk.

Every Matterport action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

0

Look things up. Allowed by default.

  • No read actions.

write

5

Create and change things. Allow, or ask the user first.

  • matterport.update_model_state
    Update Model State
  • matterport.model
    Get Model by ID
  • matterport.models
    Query Matterport Models
  • matterport.room_classifications
    List Room Classifications
  • matterport.model_event_webhook_callbacks
    Get Model Event Webhook Callbacks

destructive

1

Delete, cancel or archive. Ask first, or deny outright.

  • matterport.delete_model
    Delete Matterport Model
03 · HOW IT WORKS

Matterport in three steps.

  1. 01Your users connect MatterportThey sign in to Matterport on Arc0 Connect, under your brand, and approve the access you ask for.
  2. 02You set the rulesReads run, writes like “update Model State” can wait for the user, and “delete Matterport Model” can be denied outright.
  3. 03Any agent can actYour agent calls Matterport through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('matterport', {
  read: 'allow',
  write: 'ask',        // update_model_state
  destructive: 'deny',  // delete_model
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Matterport connects.

Users sign in to Matterport on Arc0 Connect and approve the scopes you request. Build with Arc0’s Matterport OAuth app, or bring your own so the Matterport consent screen names you. Tokens refresh automatically, and you can export them whenever you want.

The same Matterport connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
Username and password · OAuth 2.0
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Matterport from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Matterport and Arc0, answered.

Q01

Can I use Matterport with Claude, ChatGPT or Cursor?

Yes. Connect Matterport to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Matterport actions you allow.

Q02

How do users connect Matterport?

Users sign in to Matterport on Arc0 Connect and approve the scopes you request. Build with Arc0’s Matterport OAuth app, or bring your own so the Matterport consent screen names you. Tokens refresh automatically, and you can export them whenever you want.

Q03

Which Matterport actions can my agent take?

6 in total: 0 read, 5 write and 1 destructive, such as “update Model State”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Matterport?

Yes. Actions like “delete Matterport Model” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Matterport too?

Yes. The same Matterport connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Matterport into your agent.

Your users connect Matterport once, under your brand. Your agent gets 6 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan