davinci-resolve-mcp

An MCP server that lets an AI client (e.g., Claude Desktop or 5ire) connect to DaVinci Resolve Studio and perform actions such as project/timeline/media management, opening pages, working with Fusion compositions, querying current state, and executing Python/Lua code inside Resolve/Fusion.

Evaluated Mar 30, 2026 (21d ago)
Repo ↗ Ai Ml mcp davinci-resolve fusion automation media-editing desktop-integration python
⚙ Agent Friendliness
48
/ 100
Can an agent use this?
🔒 Security
24
/ 100
Is it safe for agents?
⚡ Reliability
18
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
70
Documentation
55
Error Messages
0
Auth Simplicity
90
Rate Limits
0

🔒 Security

TLS Enforcement
20
Auth Strength
20
Scope Granularity
20
Dep. Hygiene
45
Secret Handling
20

Security posture is unclear from the README. There is no described auth model or TLS requirement (likely local MCP, but not guaranteed). The presence of execute_python/execute_lua is a major risk: an agent could run arbitrary code in the Resolve/Fusion environment, which could exfiltrate data via filesystem/network or cause destructive changes. No controls are documented for sandboxing, command allowlists, permissioning, safe parameter validation, or audit logging.

⚡ Reliability

Uptime/SLA
0
Version Stability
50
Breaking Changes
0
Error Recovery
20
AF Security Reliability

Best When

You want an AI assistant to drive a local DaVinci Resolve workflow (project/timeline/media/Fusion) and you can accept the security implications of the provided execution tools.

Avoid When

You cannot sandbox or restrict the assistant’s ability to call execute_python/execute_lua, or you need strong guarantees around idempotency, safety checks, and consistent error handling.

Use Cases

  • Automate DaVinci Resolve project setup and workflow via an MCP-connected assistant
  • Programmatically create or modify timelines and media pool organization
  • Generate or update Fusion node graphs (nodes/chains) through natural-language or structured tool calls
  • Extract information about the current Resolve project/timelines/media pool for agent planning
  • Run ad-hoc scripts to automate custom Resolve/Fusion tasks (Python/Lua)

Not For

  • Production environments where arbitrary code execution is not acceptable
  • Environments requiring strict change control/approvals for editing timelines/projects
  • Users who cannot run DaVinci Resolve Studio locally (server appears intended for local automation)
  • Use cases needing publicly documented, stable, versioned API contracts beyond what the MCP server provides

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: None specified (implied local MCP connection)
OAuth: No Scopes: No

No authentication mechanism is described in the provided README; access appears to rely on the client connecting to the MCP server locally or within a trusted environment.

Pricing

Free tier: No
Requires CC: No

Open-source (MIT) with local execution; no hosting/pricing information provided.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Includes high-risk actions: execute_python(code) and execute_lua(script); agents must be constrained to safe code and validated parameters.
  • Resolve/Fusion statefulness: many operations depend on the current project/timeline/media pool; agents may need to call status/current resources first to avoid acting on the wrong context.
  • Potential off-by-one / indexing assumptions are hinted by commands like set_current_timeline(index) being 1-based; agents should confirm indexing from retrieved resources.
  • Non-idempotent operations (create_project/create_timeline/import_media/add_fusion_comp_to_clip/create_fusion_node) may duplicate work if retried without guards.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for davinci-resolve-mcp.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered