Move the cursor to the start of the project (time 0).
AI agents invoke cursor_to_project_start to trigger actions in AudacityMCP. 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.
While moving a cursor is non-destructive and has minimal blast radius, it is fundamentally an Execute action—it runs a command in Audacity that changes the application's internal state. It is not a Read operation (which would only retrieve information) nor a Write operation (which would persist data structures).
From the tool's definition Tool performs an action ('Move the cursor') that triggers a state change in Audacity's playback/editing position.
Documented attack patterns abuse exactly the kind of access cursor_to_project_start gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AudacityMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for cursor_to_project_start:
{
"version": "1",
"default": "deny",
"tools": {
"cursor_to_project_start": {
"limits": [
{
"counter": "cursor_to_project_start_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}cursor_to_project_start 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.
Move the cursor to the start of the project (time 0). It is categorised as a Execute tool in the AudacityMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Audacity MCP server in PolicyLayer and add a rule for cursor_to_project_start: 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 AudacityMCP. Nothing to install.
cursor_to_project_start 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 cursor_to_project_start 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 cursor_to_project_start. 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.
cursor_to_project_start is provided by the Audacity MCP server (xdarkzx/audacity-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 131 AudacityMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
131 AudacityMCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.