{
  "markdown": "# Florence-2 MCP Server\n\n[![uv](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/uv/main/assets/badge/v0.json)](https://github.com/astral-sh/uv)\n[![Python Application](https://github.com/jkawamoto/mcp-florence2/actions/workflows/python-app.yaml/badge.svg)](https://github.com/jkawamoto/mcp-florence2/actions/workflows/python-app.yaml)\n[![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit)](https://github.com/pre-commit/pre-commit)\n[![GitHub License](https://img.shields.io/github/license/jkawamoto/mcp-florence2)](https://github.com/jkawamoto/mcp-florence2/blob/main/LICENSE)\n\n[![MseeP.ai Security Assessment Badge](https://mseep.net/pr/jkawamoto-mcp-florence2-badge.png)](https://mseep.ai/app/jkawamoto-mcp-florence2)\n\nAn MCP server for processing images using [Florence-2](https://huggingface.co/microsoft/Florence-2-large).\n\nYou can process images or PDF files stored on a local or web server to extract text using OCR (Optical Character\nRecognition) or generate descriptive captions summarizing the content of the images.\n\n## Installation\n\n### [Claude](https://claude.com/download)\nDownload the latest MCP bundle `mcp-florence2.mcpb` from\nthe [Releases](https://github.com/jkawamoto/mcp-florence2/releases) page,\nthen open the downloaded `.mcpb `file or drag it into the Claude Desktop's Settings window.\n\n<details>\n<summary>Manually configuration</summary>\n\nYou can also manually configure this server for Claude Desktop.\nEdit the `claude_desktop_config.json` file by adding the following entry under `mcpServers`:\n\n```json\n{\n  \"mcpServers\": {\n    \"florence-2\": {\n      \"command\": \"uvx\",\n      \"args\": [\n        \"--from\",\n        \"git+https://github.com/jkawamoto/mcp-florence2\",\n        \"mcp-florence2\"\n      ]\n    }\n  }\n}\n```\n\nAfter editing, restart the application.\n\n</details>\n\nFor more information,\nsee: [Connect to local MCP servers - Model Context Protocol](https://modelcontextprotocol.io/docs/develop/connect-local-servers).\n\n### [goose](https://block.github.io/goose/)\nOpen this link\n```\ngoose://extension?cmd=uvx&arg=--from&arg=git%2Bhttps%3A%2F%2Fgithub.com%2Fjkawamoto%2Fmcp-florence2&arg=mcp-florence2&id=florence2&name=Florence-2&description=An%20MCP%20server%20for%20processing%20images%20using%20Florence-2\n```\nto launch the installer, then click \"Yes\" to confirm the installation.\n\n<details>\n<summary>Manually configuration</summary>\n\nYou can also directly edit the config file (`~/.config/goose/config.yaml`) to include the following entry:\n\n```yaml\nextensions:\n  florence2:\n    name: Florence-2\n    cmd: uvx\n    args: [ --from, git+https://github.com/jkawamoto/mcp-florence2, mcp-florence2 ]\n    enabled: true\n    type: stdio\n```\n</details>\n\nFor more details on configuring MCP servers in Goose, refer to the documentation:\n[Using Extensions | goose](https://block.github.io/goose/docs/getting-started/using-extensions#mcp-servers).\n\n### [LM Studio](https://lmstudio.ai/)\nTo configure this server for LM Studio, click the button below.\n\n[![Add MCP Server florence-2 to LM Studio](https://files.lmstudio.ai/deeplink/mcp-install-light.svg)](https://lmstudio.ai/install-mcp?name=florence-2&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyItLWZyb20iLCJnaXQraHR0cHM6Ly9naXRodWIuY29tL2prYXdhbW90by9tY3AtZmxvcmVuY2UyIiwibWNwLWZsb3JlbmNlMiJdfQ%3D%3D)\n\n## Tools\n\n### ocr\n\nProcess an image file or URL using OCR to extract text.\n\n#### Arguments:\n\n- **src**: A file path or URL to the image file that needs to be processed.\n\n### caption\n\nProcesses an image file and generates captions for the image.\n\n#### Arguments:\n\n- **src**: A file path or URL to the image file that needs to be processed.\n\n### process\n\nProcesses an image file with a custom prompt using the Florence-2 model.\n\n#### Arguments:\n\n- **src**: A file path or URL to the image file that needs to be processed.\n- **prompt**: A custom prompt for the Florence-2 model.\n\n## License\n\nThis application is licensed under the MIT License. See the [LICENSE](LICENSE) file for more details.\n",
  "bytes": 4024,
  "sha": "ecc4ccd1646f19c1084326548fe630188c1b0f9a2f4210804fac40c776461565",
  "repo_slug": "jkawamoto/mcp-florence2",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_jkawamoto_mcp_florence2_7e6574f1/readme"
}