{"id":32873233,"url":"https://github.com/devisionx/tuba-workflow-mcp-server","last_synced_at":"2026-05-13T20:32:14.728Z","repository":{"id":322701797,"uuid":"1090398497","full_name":"DevisionX/Tuba-Workflow-MCP-Server","owner":"DevisionX","description":"Model Context Protocol server for Tuba Workflow","archived":false,"fork":false,"pushed_at":"2025-11-05T21:07:34.000Z","size":35,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-11-05T23:22:01.385Z","etag":null,"topics":["artificial-intelligence","computer-vision","mcp","mcp-client","mcp-server"],"latest_commit_sha":null,"homepage":"https://tuba.ai","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/DevisionX.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-11-05T16:03:28.000Z","updated_at":"2025-11-05T21:00:23.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/DevisionX/Tuba-Workflow-MCP-Server","commit_stats":null,"previous_names":["devisionx/tuba-workflow-mcp-server"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/DevisionX/Tuba-Workflow-MCP-Server","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DevisionX%2FTuba-Workflow-MCP-Server","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DevisionX%2FTuba-Workflow-MCP-Server/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DevisionX%2FTuba-Workflow-MCP-Server/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DevisionX%2FTuba-Workflow-MCP-Server/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DevisionX","download_url":"https://codeload.github.com/DevisionX/Tuba-Workflow-MCP-Server/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DevisionX%2FTuba-Workflow-MCP-Server/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":283517792,"owners_count":26849048,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-11-09T02:00:05.828Z","response_time":62,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["artificial-intelligence","computer-vision","mcp","mcp-client","mcp-server"],"created_at":"2025-11-09T14:01:01.248Z","updated_at":"2025-11-09T14:02:15.680Z","avatar_url":"https://github.com/DevisionX.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# **Tuba Workflow MCP Server**\n\nThis project is a Model Context Protocol (MCP) server that acts as a bridge to the [Tuba.ai](https://tuba.ai/) platform.\n\nTuba is an all-in-one AI vision workflow builder that streamlines the entire lifecycle of computer vision tasks. This server exposes your Tuba project's workflow as a set of callable tools, allowing other applications (like AI assistants, scripts, or services like Claude Desktop) to programmatically control and interact with your AI vision pipelines.\n\n## **Table of Contents**\n\n- [Features](#features)\n- [Getting Started](#getting-started)\n  - [Prerequisites](#prerequisites)\n  - [Installation](#installation)\n- [Configuration](#configuration)\n  - [Local Development \u0026 Testing](#local-development--testing)\n  - [Claude Desktop Configuration](#claude-desktop-configuration)\n- [Available Tools](#available-tools)\n- [Usage Examples](#usage-examples)\n- [Contributing](#contributing)\n- [License](#license)\n- [Security](#security)\n\n## **Features**\n\nThis MCP server provides the following tools to interact with the Tuba Workflow API:\n\n| Tool                              | Description                                                         |\n| --------------------------------- | ------------------------------------------------------------------- |\n| **run()**                         | Executes the workflow for your project                              |\n| **status()**                      | Retrieves the current workflow execution status                     |\n| **result()**                      | Fetches workflow results (downloads as `result.zip` if file output) |\n| **get_workflow_blocks()**         | Retrieves the current configuration of all workflow blocks          |\n| **update_workflow_blocks_data()** | Updates parameters and uploads files to workflow blocks             |\n\n## **Getting Started**\n\n### **Prerequisites**\n\n- **Python 3.10 or higher** - Required for modern type hints and async features\n- **[uv](https://github.com/astral-sh/uv)** - Fast Python package installer and environment manager\n- **A Tuba.ai account** with an active project\n- **TUBA_WORKFLOW_ACCESS_TOKEN** - Your project's API access token\n\n### **Installation**\n\n1. **Clone the repository:**\n\n   ```bash\n   git clone \u003cthis_repo\u003e\n   cd \u003cthis_repo\u003e\n   ```\n\n2. **Install uv:**\n\n   - **macOS/Linux:**\n\n     ```bash\n     curl -LsSf https://astral.sh/uv/install.sh | sh\n     ```\n\n   - **Windows:**\n     ```powershell\n     powershell -ExecutionPolicy ByPass -c \"irm https://astral.sh/uv/install.ps1 | iex\"\n     ```\n\n3. **Create a virtual environment and install dependencies:**\n   ```bash\n   uv venv\n   uv pip install -r requirements-lock.txt\n   ```\n\n## **Configuration**\n\n### **Local Development \u0026 Testing**\n\nFor local development, the server loads your access token from an environment file using `python-dotenv`.\n\n1. **Create a `.env` file** in the project root:\n\n   ```bash\n   touch .env\n   ```\n\n2. **Add your access token:**\n\n   ```env\n   TUBA_WORKFLOW_ACCESS_TOKEN=\"your_secret_token_goes_here\"\n   ```\n\n   \u003e **Note:** The `.gitignore` file ensures this file is never committed to version control.\n\n3. **Test the server:**\n\n   ```bash\n   uv run python tuba_workflow_mcp_server.py\n   ```\n\n4. **Verify it's working:**\n   The server should start without errors. You can test it by connecting an MCP client or using the tools through Claude Desktop.\n\n### **Claude Desktop Configuration**\n\nTo use this server with Claude Desktop, add the following configuration to your `claude_desktop_config.json` file:\n\n**macOS/Linux Location:**\n\n```\n~/Library/Application Support/Claude/claude_desktop_config.json\n```\n\n**Windows Location:**\n\n```\n%APPDATA%\\Claude\\claude_desktop_config.json\n```\n\n**Configuration:**\n\n```json\n{\n  \"mcpServers\": {\n    \"TubaWorkflow\": {\n      \"command\": \"\u003chome_path\u003e/.local/bin/uv\",\n      \"args\": [\n        \"run\",\n        \"--directory\",\n        \"\u003cabsolute_path_to_tuba_workflow_mcp_server_folder\u003e\",\n        \"python\",\n        \"tuba_workflow_mcp_server.py\"\n      ],\n      \"env\": {\n        \"TUBA_WORKFLOW_ACCESS_TOKEN\": \"\u003cyour_access_token\u003e\"\n      }\n    }\n  }\n}\n```\n\n**Replace the placeholders:**\n\n- `\u003chome_path\u003e` - Your home directory path (e.g., `/Users/yourname` or `C:\\Users\\yourname`)\n- `\u003cabsolute_path_to_tuba_workflow_mcp_server_folder\u003e` - Full path to this project folder\n- `\u003cyour_access_token\u003e` - Your Tuba.ai workflow access token\n\n**Example (macOS):**\n\n```json\n{\n  \"mcpServers\": {\n    \"TubaWorkflow\": {\n      \"command\": \"/Users/john/.local/bin/uv\",\n      \"args\": [\n        \"run\",\n        \"--directory\",\n        \"/Users/john/projects/tuba-workflow-mcp-server\",\n        \"python\",\n        \"tuba_workflow_mcp_server.py\"\n      ],\n      \"env\": {\n        \"TUBA_WORKFLOW_ACCESS_TOKEN\": \"\u003cyour_access_token\u003e\"\n      }\n    }\n  }\n}\n```\n\nAfter configuration, restart Claude Desktop to load the MCP server.\n\n## **Available Tools**\n\n### **run()**\n\nExecutes the workflow for your authenticated project.\n\n---\n\n### **status()**\n\nRetrieves the current status of the workflow execution.\n\n---\n\n### **result()**\n\nFetches the results of the workflow execution. If the result is a file (e.g., processed images, videos), it will be automatically saved as `result.zip` in your current working directory.\n\n---\n\n### **get_workflow_blocks()**\n\nRetrieves the current configuration of all workflow blocks in your project. Use this to discover available block IDs and their current parameter values.\n\n---\n\n### **update_workflow_blocks_data()**\n\nUpdates parameters and uploads files to workflow blocks. Supports three file upload methods:\n\n- **Local files** - Upload from file paths on your system\n- **Remote URLs** - Fetch and upload files from web URLs\n- **Base64 data** - Upload files encoded as base64 strings\n\n**File Field Naming Convention:**\nFile field names should follow this format: `\u003cblock_id\u003e_\u003cparam_name\u003e`\n\n## **Usage Examples**\n\nOnce configured with Claude Desktop (or another MCP client), you can interact with your Tuba workflow using natural language. The AI assistant will handle all the technical details like finding block IDs, formatting JSON correctly, handling file paths, and monitoring workflow progress.\n\n**Example conversations:**\n\n- \"Can you check the status of my Tuba workflow?\"\n- \"Start my workflow and let me know when it's done\"\n- \"Update the confidence threshold to 0.8 for my object detector\"\n- \"Process this image with my workflow: /path/to/image.jpg\"\n- \"Upload these three images from URLs and run the workflow\"\n- \"Show me my workflow configuration\"\n\n## **Contributing**\n\nWe welcome contributions! Please see our [Code of Conduct](CODE_OF_CONDUCT.md) for community guidelines.\n\n**Before contributing:**\n\n1. Check existing issues and pull requests\n2. Follow the existing code style\n3. Add tests for new features\n4. Update documentation as needed\n\nFor major changes, please open an issue first to discuss what you would like to change.\n\n## **License**\n\nThis project is licensed under the **MIT License** - see the [LICENSE](LICENSE) file for details.\n\n## **Security**\n\nSecurity is a top priority. If you discover a vulnerability, please report it responsibly.\n\n**Do not open public GitHub issues for security vulnerabilities.**\n\nInstead, use GitHub's private vulnerability reporting feature:\n\n1. Navigate to the **Security** tab\n2. Click **Report a Vulnerability**\n3. Provide detailed information about the issue\n\nSee [SECURITY.md](SECURITY.md) for more information.\n\n---\n\n## **Resources**\n\n- [Tuba.ai Platform](https://tuba.ai/)\n- [Model Context Protocol (MCP) Specification](https://modelcontextprotocol.io/)\n- [FastMCP Documentation](https://github.com/jlowin/fastmcp)\n\n## **Support**\n\nFor questions, issues, or feedback:\n\n- **Tuba.ai Support:** support@tuba.ai\n- **Join Discord Community** https://discord.com/invite/gDSZr6N5rC\n- **GitHub Issues:** Use for bug reports and feature requests\n- **Discussions:** Use GitHub Discussions for questions and community interaction\n\n---\n\n**Copyright © 2025 DevisionX. All rights reserved.**\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdevisionx%2Ftuba-workflow-mcp-server","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdevisionx%2Ftuba-workflow-mcp-server","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdevisionx%2Ftuba-workflow-mcp-server/lists"}