{
  "markdown": "# Pedra MCP Server\n\nOfficial [Model Context Protocol](https://modelcontextprotocol.io) server for the [Pedra API](https://pedra.ai/api-documentation) — use Pedra's AI real-estate photo editing (virtual staging, renovation, room emptying, enhancement, sky replacement, object removal/blur, and property videos) directly from **Claude, ChatGPT, Cursor**, and any other MCP client.\n\n[![npm version](https://img.shields.io/npm/v/@pedra-ai/mcp.svg)](https://www.npmjs.com/package/@pedra-ai/mcp)\n[![Official MCP registry](https://img.shields.io/badge/MCP%20registry-pedra--mcp-blue)](https://registry.modelcontextprotocol.io)\n\n[![Add to Cursor](https://cursor.com/deeplink/mcp-install-dark.svg)](cursor://anysphere.cursor-deeplink/mcp/install?name=pedra&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBwZWRyYS1haS9tY3AiXSwiZW52Ijp7IlBFRFJBX0FQSV9LRVkiOiJZT1VSX1BFRFJBX0FQSV9LRVkifX0=)\n\nIt exposes **one tool per API endpoint**. Each tool is a single blocking call that returns the final asset URL(s) — there are no job IDs to poll.\n\n## Quick start\n\nYou need a Pedra API key — get one from your [Pedra account](https://app.pedra.ai). The server reads it from the `PEDRA_API_KEY` environment variable.\n\nThe server runs over stdio and is published to npm, so most clients just run it with `npx` — no global install needed.\n\n### Claude Desktop (one-click)\n\nDownload the latest **`pedra-mcp.mcpb`** from [Releases](https://github.com/pedra-ai/pedra-mcp/releases) and double-click it (or drag it into Claude Desktop → Settings → Extensions). Claude installs the bundled server and prompts for your `PEDRA_API_KEY` — no JSON editing.\n\n### Claude Desktop (manual)\n\nOr add this to your `claude_desktop_config.json` (Settings → Developer → Edit Config):\n\n```json\n{\n  \"mcpServers\": {\n    \"pedra\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@pedra-ai/mcp\"],\n      \"env\": { \"PEDRA_API_KEY\": \"your-api-key\" }\n    }\n  }\n}\n```\n\n### Cursor\n\nIn `~/.cursor/mcp.json` (or `.cursor/mcp.json` in a project):\n\n```json\n{\n  \"mcpServers\": {\n    \"pedra\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@pedra-ai/mcp\"],\n      \"env\": { \"PEDRA_API_KEY\": \"your-api-key\" }\n    }\n  }\n}\n```\n\n### Any MCP client\n\nRun the binary directly with the key in the environment:\n\n```bash\nPEDRA_API_KEY=your-api-key npx -y @pedra-ai/mcp\n```\n\nOr install it:\n\n```bash\nnpm install -g @pedra-ai/mcp\nPEDRA_API_KEY=your-api-key pedra-mcp\n```\n\n### Smithery\n\nYou can also install and configure Pedra automatically via [Smithery](https://smithery.ai/server/@pedra-ai/mcp):\n\n```bash\nnpx -y @smithery/cli install @pedra-ai/mcp --client claude\n```\n\n(swap `claude` for `cursor`, `windsurf`, etc.) Smithery prompts for your `PEDRA_API_KEY` and writes the client config for you.\n\n## Tools\n\n| Tool | Endpoint | What it does |\n|------|----------|--------------|\n| `pedra_enhance` | `/enhance` | Improve lighting, color, sharpness |\n| `pedra_enhance_and_correct_perspective` | `/enhance_and_correct_perspective` | Enhance + straighten perspective |\n| `pedra_empty_room` | `/empty_room` | Remove all furniture/objects |\n| `pedra_furnish` | `/furnish` | Virtually stage a room |\n| `pedra_renovation` | `/renovation` | Renovate walls/floors/finishes |\n| `pedra_edit_via_prompt` | `/edit_via_prompt` | Edit from a natural-language prompt |\n| `pedra_sky_blue` | `/sky_blue` | Replace a dull sky with clear blue |\n| `pedra_remove_object` | `/remove_object` | Remove an object using a mask |\n| `pedra_blur` | `/blur` | Blur faces, license plates, etc. |\n| `pedra_create_video` | `/create_video` | Render a property video from images |\n| `pedra_update_video` | `/update_video` | Edit a video without re-rendering unchanged clips |\n| `pedra_generate_voice_script` | `/generate_voice_script` | Write a voiceover script from property photos |\n| `pedra_generate_voice` | `/generate_voice` | Turn a script into a voiceover audio track |\n| `pedra_music_library` | `/music_library` | List background-music tracks + voice languages |\n| `pedra_list_properties` | `/list_properties` | List the account's properties |\n| `pedra_list_property_images` | `/list_property_images` | List a property's photos as URLs |\n| `pedra_create_property` | `/create_property` | Create a property |\n| `pedra_add_images_to_property` | `/add_images_to_property` | Add photos to a property by URL |\n| `pedra_credits` | `/credits` | Read plan + remaining credits |\n| `pedra_feedback` | `/feedback` | Thumbs up/down + optional credit-back |\n\nMost image tools take an `imageUrl` plus a few optional parameters; see each tool's input schema in your MCP client. The `imageUrl` (and `maskUrl`, and each `create_video` frame) accepts any of:\n\n- a public `https://` URL,\n- a `data:` URI, or\n- an **absolute path to a local image file** — the server reads it off disk and inlines it as base64 for you, so you can point a tool at a file you just dragged in without hosting it first (`.jpg`, `.jpeg`, `.png`, `.webp`, `.gif`, `.bmp`, `.tif/.tiff`, `.heic/.heif`, `.avif`; up to 40 MB).\n\n> Note: an image **pasted into the chat** is not a file path, so it can't be forwarded to the tool — drag in a file, or save the paste and pass its path.\n\nExample prompts once connected:\n\n> \"Use Pedra to virtually stage https://example.com/empty-living-room.jpg as a minimalist living room.\"\n\n> \"Virtually stage /Users/me/Desktop/empty-living-room.jpg as a minimalist living room.\"\n\n> \"How many Pedra credits do I have left?\"\n\n## How it works\n\nThis server is a thin wrapper over [`@pedra-ai/sdk`](https://www.npmjs.com/package/@pedra-ai/sdk), which encodes the API's contract details:\n\n- **Synchronous by design.** Every endpoint blocks and returns the final URL(s) in the response body. Even `pedra_create_video` polls server-side and returns the finished `videoUrl` inline (it can take up to ~10 minutes; the API keeps the connection alive with a heartbeat).\n- **Errors are tool errors.** The API's 4xx responses (insufficient credits, bad image, …) come back as MCP tool errors with a readable message, not crashes.\n\n## Privacy Policy\n\nThis server sends the image/video URLs and parameters you pass to the [Pedra API](https://pedra.ai) to perform the requested edit, authenticated with your `PEDRA_API_KEY`. It stores no data itself. Data collection, usage, storage, retention, third-party sharing, and contact information are covered by Pedra's privacy policy: **https://pedra.ai/privacy**.\n\n## License\n\nMIT © Pedra\n",
  "bytes": 6395,
  "sha": "d81888bcd9f56e30dbc0e69405bb27bc45a29ee355975535e5267b37c6ba27ec",
  "repo_slug": "pedra-ai/pedra-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_pedra_ai_pedra_mcp_608d0eb1/readme"
}