VisionAgent MCP Server

- Translates MCP tool calls into authenticated VisionAgent API requests.
- Supports agentic document analysis, text‑to‑object detection, text‑to‑instance segmentation, activity recognition, and depth estimation.
- Auto‑generates tool definitions from a live OpenAPI spec via npm run generate-tools.
- Renders masks, bounding boxes, and depth maps to files or inline previews.
- Validates arguments with Zod schemas derived from the OpenAPI spec.
- Outputs JSON and media results streamed back to the MCP client.

| Software | Minimum Version |
| ------------------------ | ---------------------------------------- |
| Node.js | 20 (LTS) |
| VisionAgent account | Any paid or free tier (needs API key) |
| MCP client | Claude Desktop / Cursor / Cline / etc. |

npm install -g vision-tools-mcp

{
"mcpServers": {
"VisionAgent": {
"command": "npx",
"args": ["vision-tools-mcp"],
"env": {
"VISION_AGENT_API_KEY": "<YOUR_API_KEY>",
"OUTPUT_DIRECTORY": "/path/to/output/directory",
"IMAGE_DISPLAY_ENABLED": "true" # or false, see below
}
}
}
}

4. Open your MCP-aware client.

5. Download street.png (from the assets folder in this directory, or you can choose any test image).

6. Paste the prompt below (or any prompt):

If your client supports inline resources, you’ll see bounding-box overlays; otherwise, the PNG is saved to your output directory, and the chat shows its path.

| ENV var                 | Required | Default    | Purpose                                                |

| ----------------------- | -------- | ---------- | ------------------------------------------------------ |

| VISION_AGENT_API_KEY  | Yes  | —          | Landing AI auth token.                                 |

| OUTPUT_DIRECTORY      | No       | —          | Where rendered images / masks / depth maps are stored. |

| IMAGE_DISPLAY_ENABLED | No       | true     | false ➜ skip rendering                               |
1. Clone the repository:

2. Navigate into the project directory:

3. Install dependencies:

4. Build the project:

- VISION_AGENT_API_KEY - Required API key for VisionAgent authentication

- OUTPUT_DIRECTORY - Optional directory for saving processed outputs (supports relative and absolute paths)

- IMAGE_DISPLAY_ENABLED - Set to "true" to enable image visualization features

After building, configure your MCP client with the following settings:

> Note: Replace /path/to/build/index.js with the actual path to your built index.js` file, and set your environment variables as needed. For MCP clients without image display capabilities, like Cursor, set IMAGE_DISPLAY_ENABLED to False. For MCP clients with image display capabilities, like Claude Desktop, set IMAGE_DISPLAY_ENABLED to true to visualize tool outputs. Generally, MCP clients that support resources (see this list: https://modelcontextprotocol.io/clients) will support image display.