AI agents use project_import_midi to create or update resources in AudacityMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AudacityMCP environment.
Importing a MIDI file is a Write operation because it modifies the current project by adding new content. While reversible (can be undone in Audacity), it creates/incorporates new data into the project state. Severity is medium because misuse could pollute a project with unwanted MIDI data, requiring manual cleanup, but the effect is reversible and limited to the current project scope.
From the tool's definition Tool name 'project_import_midi' and description 'Import a MIDI file into the current project' indicate the tool adds or loads data into an existing project, modifying its state by incorporating new audio/MIDI content.
Documented attack patterns abuse exactly the kind of access project_import_midi 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 project_import_midi:
{
"version": "1",
"default": "deny",
"tools": {
"project_import_midi": {
"limits": [
{
"counter": "project_import_midi_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} project_import_midi 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.
Import a MIDI file into the current project. It is categorised as a Write tool in the AudacityMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Audacity MCP server in PolicyLayer and add a rule for project_import_midi: 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.
project_import_midi 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 project_import_midi 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 project_import_midi. 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.
project_import_midi 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.