Get the label of a node. Args: node_index: 1-based node index. item_index: 0-based timeline item index. Default: 0. track_type: 'video' or 'audio'. Default: 'video'. track_index: 1-based track index. Default: 1.
AI agents call graph_get_node_label to retrieve information from DaVinci Resolve MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata (a node's label) from the DaVinci Resolve graph structure without modifying, creating, deleting, or executing any operations. It simply queries and returns information about an existing node. No data is written, no external commands are executed, and no irreversible changes occur. This is a straightforward read operation with minimal risk.
From the tool's definition Tool is named 'graph_get_node_label' and description states 'Get the label of a node.' The verb 'Get' and action of retrieving a label indicates a read-only query operation with no side effects.
Documented attack patterns abuse exactly the kind of access graph_get_node_label 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 graph_get_node_label:
{
"version": "1",
"default": "deny",
"tools": {
"graph_get_node_label": {}
}
}graph_get_node_label is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get the label of a node. Args: node_index: 1-based node index. item_index: 0-based timeline item index. Default: 0. track_type: 'video' or 'audio'. Default: 'video'. track_index: 1-based track index. Default: 1. It is categorised as a Read tool in the DaVinci Resolve MCP MCP Server, which means it retrieves data without modifying state.
Register the DaVinci Resolve MCP server in PolicyLayer and add a rule for graph_get_node_label: 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.
graph_get_node_label is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the graph_get_node_label 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 graph_get_node_label. 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.
graph_get_node_label 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.