MCP server

Connect Pedra to Claude, ChatGPT, Cursor, and any MCP client. The official Model Context Protocol server exposes one tool per Pedra endpoint — virtual staging, renovation, image enhancement, and listing videos — as blocking calls that return the final asset URL.

Official MCP server

Open source, MIT-licensed, and published to npm as @pedra-ai/mcp. It exposes one tool per API endpoint; each tool is a single blocking call that returns the final asset URL(s) — no job IDs to poll. Under the hood it's a thin wrapper over the Pedra Node SDK.

Use it in Claude (web, mobile & desktop)

In Claude, open Settings → Connectors → Add custom connector, paste the URL above, and click Connect — you sign in to Pedra once and approve access. No API key to copy and paste. It works in Claude on web, mobile, and desktop, and runs on your account's credits.

In ChatGPT: Pedra is an official ChatGPT plugin. Open Plugins in the ChatGPT sidebar, search for Pedra and click Install plugin. See how to make a listing video with ChatGPT or Claude.

What you can do

Once connected, ask your assistant in plain language — it picks the right tool and returns the finished image or video URL:

"Use Pedra to virtually stage https://example.com/empty-living-room.jpg as a minimalist living room."

"Empty this furnished bedroom so I can show the bare room: https://example.com/bedroom.jpg"

"Renovate this dated kitchen in a Scandinavian style: https://example.com/kitchen.jpg"

"Add a large green plant in the corner of this living room: https://example.com/living.jpg"

"Brighten and straighten the photo I just attached."

"Swap the grey sky in this exterior shot for clear blue: https://example.com/facade.jpg"

"Blur the faces and license plates in this street-facing photo: https://example.com/street.jpg"

"Make a listing video from these 8 photos with music and a '3 bed · 2 bath' caption."

"Build a virtual tour of Calle Mayor 12 from my 360° photos and give me the embed code."

"How many Pedra credits do I have left?"

Photos from the chat

Photos already in your Pedra account are the easiest source — just ask, e.g. "build a video from my Calle Mayor listing photos", and the assistant lists your properties, reads their image URLs, and renders the video. A photo on the web works too: give its URL and the server fetches it. For photos you have with you:

• ChatGPT: attach them. Photos attached to the chat go straight to the tools. Attach a photo and say "stage this living room": the nine single-photo tools (pedra_furnish, pedra_enhance, pedra_empty_room and the rest) take it as imageFile instead of imageUrl, and pedra_add_images_to_property takes several as files.
• Claude, or photos still on your phone: an upload link. Claude doesn't pass chat attachments to tools, so the assistant calls pedra_create_upload_link and gives you a no-login link, valid 24 hours. Open it on your phone (HEIC from an iPhone works) or send it to the photographer, drop the photos in, and tell the assistant when you're done. It then lists them with pedra_list_property_images and carries on — edits, pedra_create_video or pedra_create_virtual_tour. The link takes regular photos and 360° photos by default (type: "any"); see create_upload_link.

Photos brought in from outside the app count toward a daily upload limit (30 a day on the free plan, 500 on paid plans).

New to Pedra?

No account needed beforehand. Connecting Pedra in ChatGPT or Claude opens a Pedra sign-in tab, and new users can create their account right there. Other agents — Claude Code, scripts, the local MCP server — can get an account and API key for their user by email with agent_signup.

Other clients & local setup (Cursor, scripts, Claude Desktop config)

For Claude, prefer the hosted connector above. For Cursor, local scripts, or editing Claude Desktop's config file directly, run the npm package over stdio — it launches with npx (no global install) and reads your key from the PEDRA_API_KEY environment variable.

{
  "mcpServers": {
    "pedra": {
      "command": "npx",
      "args": ["-y", "@pedra-ai/mcp"],
      "env": { "PEDRA_API_KEY": "your-api-key" }
    }
  }
}

In Claude Desktop, open Settings → Developer → Edit Config and add the pedra entry. In Cursor, use ~/.cursor/mcp.json (or .cursor/mcp.json in a project). Restart the client after saving.

Authentication

The server reads your key from PEDRA_API_KEY. Get one by signing up at app.pedra.ai and opening Settings → API. See Authentication for details.

Tools

One tool per endpoint, all returning final URLs:

• pedra_furnish, pedra_empty_room, pedra_renovation, pedra_edit_via_prompt, pedra_remove_object — see Virtual staging.
• pedra_enhance, pedra_enhance_and_correct_perspective, pedra_sky_blue, pedra_blur — see Image enhancement.
• pedra_create_video, pedra_update_video, pedra_generate_voice_script, pedra_generate_voice, pedra_music_library, plus pedra_credits and pedra_feedback — see Video and Credits.
• pedra_list_properties, pedra_list_property_images, pedra_create_property, pedra_add_images_to_property — browse your library and add photos so any tool can use them.
• pedra_create_upload_link, pedra_create_virtual_tour, pedra_get_virtual_tour, pedra_list_virtual_tours, pedra_update_virtual_tour, pedra_add_virtual_tour_scenes — build and edit hosted 360° virtual tours; see Virtual tours. Deleting a tour is API-only (/api/delete_virtual_tour), on purpose.
• pedra_social_accounts, pedra_social_post, pedra_social_list_posts, pedra_social_cancel_post: post or schedule a video on Instagram, Facebook, TikTok and YouTube (Pedra Pro). Remote server only for now; the npm package doesn't have them yet. See Social.

Most image tools take an imageUrl — a public URL, a data: URI, or an absolute path to a local file (read and inlined for you). Plus a few optional parameters — your client shows each tool's input schema. In ChatGPT, an attached photo goes to the tool as imageFile; in Claude, an image pasted into the chat isn't sent to the tool — pass a path or use an upload link (see Photos from the chat). Every image and video tool also accepts an optional propertyId: pass it and the result is saved into that property's gallery — visible and editable from the app — instead of only coming back as a URL. See Properties.

Build a virtual tour from chat

The 360° photos are usually on a phone or a 360° camera, and a chat can't pass large files to a tool. So the assistant hands you an upload link instead — ask something like "Make a virtual tour of Calle Mayor 12 from my 360° photos" and it runs:

1. pedra_create_upload_link — you get a no-login link, valid 24 hours. Open it on your phone (or send it to the photographer) and drop the photos in.
2. pedra_create_virtual_tour with that propertyId — once you say you're done, it builds the tour from every uploaded photo, in file-name order.
3. pedra_get_virtual_tour — building is the one asynchronous flow, so the assistant checks back until the tour is ready (about 10 seconds per room).
4. It shares the tourUrl and the embedCode iframe. Ask for changes in plain words — "rename the second bedroom to Office", "start the tour in the living room" — and it calls pedra_update_virtual_tour.

If the 360° photos are already online, skip the upload link: give the URLs and the assistant passes them straight to pedra_create_virtual_tour as scenes.

How it works

A thin wrapper over the Pedra Node SDK. Every endpoint blocks and returns the final URL(s) inline — even pedra_create_video, which can take up to ~10 minutes (the API keeps the connection alive with a heartbeat). API errors — insufficient credits, a bad image — come back as readable MCP tool errors, not crashes.

Source & support

The server is MIT-licensed and developed in the open at github.com/pedra-ai/pedra-mcp. Learn more about the protocol at modelcontextprotocol.io, and email felix@pedra.ai for integration help, higher quotas, or enterprise terms.

Frequently asked questions