AI agents use open_project to create or update resources in DaVinci MCP Professional — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your DaVinci MCP Professional environment.
Opening a project constitutes a reversible state change to the editing application (Write category). It is not a Read operation since it has side effects beyond querying data. It is not Execute since it does not run arbitrary code or commands. It is not Destructive because the action is reversible and no data is deleted or permanently modified.
From the tool's definition Tool name 'open_project' and description 'Open a project by name' indicates state modification of the DaVinci Resolve application—changing which project is currently active.
Documented attack patterns abuse exactly the kind of access open_project gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and DaVinci MCP Professional, and nothing reaches the server without passing your rules. This is the rule we recommend for open_project:
{
"version": "1",
"default": "deny",
"tools": {
"open_project": {
"limits": [
{
"counter": "open_project_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}open_project stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Open a project by name. It is categorised as a Write tool in the DaVinci MCP Professional MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the DaVinci MCP Professional MCP server in PolicyLayer and add a rule for open_project: 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 MCP Professional. Nothing to install.
open_project is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the open_project 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 open_project. 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.
open_project is provided by the DaVinci MCP Professional MCP server (positronikal/davinci-mcp-professional). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from DaVinci MCP Professional, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
13 DaVinci MCP Professional tools catalogued and risk-classified — across an index of 43,000+ MCP servers.