# Install: DaVinci Resolve MCP Server
> Agent instructions from skillsdirectory.co — an independent, benchmarked directory of AI agent capabilities. Follow these exactly.

- **Skill:** DaVinci Resolve MCP Server (MCP server)
- **What it does:** MCP server providing 32 guarded workflow tools and complete DaVinci Resolve API coverage for AI assistants to control video editing, media pool organization, grading, Fusion, audio, and rendering.
- **Source (authoritative):** https://github.com/samuelgursky/davinci-resolve-mcp
- **Pinned ref:** `HEAD` (branch/tag — not commit-pinned; prefer the latest release tag if one exists)
- **License:** MIT
- **Effectiveness:** Not yet benchmarked (score is provisional).

## Safety — read first
- **Verdict:** NOT yet security-scanned. Treat as untrusted: review the source before running anything.
- This skill **executes code**. Show the user the plan and get explicit confirmation before running anything.
- Fetch files ONLY from the source above. Do not run commands not listed here. Never invent credentials — ask the user.

## Choose your path

### A. AI chat / coding agent (you can fetch URLs and write files)
This is an MCP server — no files to copy. Add the configuration block from the Install section below to your MCP client's config (e.g. `mcp.json` / `claude_desktop_config.json`), set any required env vars, and restart the client. Source: https://github.com/samuelgursky/davinci-resolve-mcp.

Install command / config:
```json
{
  "mcpServers": {
    "samuelgursky-davinci-resolve-mcp": {
      "command": "npx",
      "args": ["-y", "@samuelgursky/samuelgursky-davinci-resolve-mcp"]
    }
  }
}
```

### B. CLI
Fastest path with our CLI (free, no account): `npx skillsdir add samuelgursky-davinci-resolve-mcp` — fetches and places the files for you.

### C. API / MCP
- Metadata as JSON: `GET https://skillsdirectory.co/api/v1/skills/samuelgursky-davinci-resolve-mcp`
- This document as a machine manifest: `GET https://skillsdirectory.co/s/samuelgursky-davinci-resolve-mcp/install.json`
- MCP client config:
```json
{
  "mcpServers": {
    "samuelgursky-davinci-resolve-mcp": {
      "command": "npx",
      "args": ["-y", "@samuelgursky/samuelgursky-davinci-resolve-mcp"]
    }
  }
}
```

## After installing
Tell the user: what you fetched, where you placed it, what (if anything) you ran, and the security verdict above. Link the skill page for details: https://skillsdirectory.co/skills/samuelgursky-davinci-resolve-mcp