DaVinci Resolve MCP Server

What does “DaVinci Resolve” MCP Server do?

The DaVinci Resolve MCP Server is an integration tool designed to bridge AI assistants and the DaVinci Resolve video editing software via the Model Context Protocol (MCP). By acting as a middleware server, it enables automated, AI-driven interactions with DaVinci Resolve, such as controlling editing actions, querying project information, or triggering exports. This empowers developers and creators to build intelligent workflows that can leverage DaVinci Resolve’s powerful editing capabilities through programmatic access, enhancing productivity, automating repetitive tasks, and integrating with broader AI-powered pipelines for content creation and management.

List of Prompts

No information about prompt templates could be found in the repository.

List of Resources

No explicit resource definitions were found in the repository or documentation.

List of Tools

No clear tool definitions are present in resolve_mcp_server.py or elsewhere in the repository.

Use Cases of this MCP Server

• Automated Video Editing
  Use AI agents to edit video timelines, apply transitions, or manage clips in DaVinci Resolve, streamlining common editing workflows.
• Project Metadata Extraction
  Query and collect metadata from DaVinci Resolve projects for cataloging, analytics, or integration with asset management systems.
• Batch Export Automation
  Trigger and manage media exports programmatically, allowing for batch processing and AI-driven export logic.
• Remote Collaboration
  Enable remote or automated agents to interact with DaVinci Resolve projects, supporting collaborative editing scenarios.
• Custom Workflow Integration
  Connect DaVinci Resolve with external APIs or tools (e.g., cloud storage, transcription services) through AI-driven automation.

How to set it up

Windsurf

1. Ensure that Python (as required by DaVinci Resolve MCP Server) is installed.
2. Clone the repository:
   git clone https://github.com/samuelgursky/davinci-resolve-mcp.git
3. Install dependencies:
   pip install -r requirements.txt
4. Add the server to Windsurf’s configuration, e.g., in windsurf.config.json:

   {
     "mcpServers": {
       "davinci-resolve": {
         "command": "python",
         "args": ["resolve_mcp_server.py"]
       }
     }
   }
   

5. Save the configuration and restart Windsurf. Verify server connectivity.

Claude

1. Ensure Python is available on your system.
2. Clone the repo and install dependencies as above.
3. Open Claude’s MCP configuration file.
4. Add the DaVinci Resolve MCP Server:

   {
     "mcpServers": {
       "davinci-resolve": {
         "command": "python",
         "args": ["resolve_mcp_server.py"]
       }
     }
   }
   

5. Save and restart Claude, then verify connection.

Cursor

1. Confirm Python and DaVinci Resolve MCP Server dependencies.
2. Download or clone the MCP server repo.
3. Open Cursor’s configuration file for MCP servers.
4. Add the following:

   {
     "mcpServers": {
       "davinci-resolve": {
         "command": "python",
         "args": ["resolve_mcp_server.py"]
       }
     }
   }
   

5. Save and restart Cursor.

Cline

1. Install all prerequisites (Python, repository dependencies).
2. Clone the repository.
3. Open Cline’s MCP server configuration.
4. Add the server:

   {
     "mcpServers": {
       "davinci-resolve": {
         "command": "python",
         "args": ["resolve_mcp_server.py"]
       }
     }
   }
   

5. Save the file and restart Cline.

Securing API Keys

For any sensitive environment variables (e.g., API keys), use the env and inputs keys in your configuration as follows:

{
  "mcpServers": {
    "davinci-resolve": {
      "command": "python",
      "args": ["resolve_mcp_server.py"],
      "env": {
        "API_KEY": "${API_KEY}"
      },
      "inputs": {
        "api_key": "${API_KEY}"
      }
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "davinci-resolve": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “davinci-resolve” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Roots support: ⛔ Not mentioned
Sampling support: ⛔ Not mentioned

Based on the available information and the completeness of the documentation, I would rate this MCP server a 4 out of 10. While setup instructions are clear and use cases are described, the lack of documented resources, tools, and prompts limits its practical utility for developers seeking a plug-and-play experience.

MCP Score