App-level DaVinci Resolve operations. Actions: launch() -> {success, message} — Launch DaVinci Resolve if not running. Call this FIRST if any tool returns a 'Not connected' error. get_version() -> {product, version, version_string} mcp_update_status(force_check?) -> {version, update, decision} se...
AI agents invoke resolve_control to trigger actions in DaVinci Resolve MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers external operations (launching DaVinci Resolve) and modifies application-level settings (update policies). Launching external software and changing system/app configuration policies goes beyond simple reads or writes — it executes operations with side effects on the host environment.
From the tool's definition Actions include launch() — Launch DaVinci Resolve if not running, get_version(), mcp_update_status, set_mcp_update_policy, ignore_mcp_update, snooze_mcp_update, clear_mcp_update_preferences — these are app-level operations that trigger external application…
Documented attack patterns abuse exactly the kind of access resolve_control gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and DaVinci Resolve MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for resolve_control:
{
"version": "1",
"default": "deny",
"tools": {
"resolve_control": {
"limits": [
{
"counter": "resolve_control_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}resolve_control stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
App-level DaVinci Resolve operations. Actions: launch() -> {success, message} — Launch DaVinci Resolve if not running. Call this FIRST if any tool returns a 'Not connected' error. get_version() -> {product, version, version_string} mcp_update_status(force_check?) -> {version, update, decision} set_mcp_update_policy(mode) -> {success, version, update, decision} ignore_mcp_update() -> {success, version, update, decision} snooze_mcp_update(hours?) -> {success, version, update, decision} clear_mcp_update_preferences() -> {success, version, update, decision} api_truth(query?) -> {verified_on, count, facts} — look up behaviorally-verified facts about quirky/unreliable Resolve API behavior (no connection needed). verification_stats() -> {stats} — readback-verification tally (verified/contradicted/unverified) since server start (no connection needed). get_page() -> {page} open_page(page) -> {success} — page: edit, cut, color, fusion, fairlight, deliver get_keyframe_mode() -> {mode} set_keyframe_mode(mode) -> {success} quit() -> {success} get_fairlight_presets() -> {presets} set_high_priority() -> {success} disable_background_tasks_for_current_session() -> {success} — Resolve 21+ open_control_panel(port?, host?, open_browser?) -> {success, url, pid, port, status} — Launches the analysis control panel (src/analysis_dashboard.py) as a background process. Idempotent: returns the existing URL if already running. control_panel_status() -> {running, pid, port, url} close_control_panel() -> {success, was_running} save_state() -> {state_token, page, current_timeline_id, current_timecode, selected_clip_ids} — Captures the current Resolve UI state so it can be restored after a preview. restore_state(state_token) -> {success, restored: {...}} — Returns Resolve to a previously-saved state. It is categorised as a Execute tool in the DaVinci Resolve MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the DaVinci Resolve MCP server in PolicyLayer and add a rule for resolve_control: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches DaVinci Resolve MCP. Nothing to install.
resolve_control is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the resolve_control rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for resolve_control. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
resolve_control is provided by the DaVinci Resolve MCP server (samuelgursky/davinci-resolve-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 369 DaVinci Resolve MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
369 DaVinci Resolve MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.