AI agents call resolve_track to retrieve information from Orpheus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool only looks up and identifies a track by name or role using fuzzy matching. It retrieves/resolves a reference to a track and may ask for clarification, but does not modify, execute, or delete anything. Pure read/query operation.
From the tool's definition Fuzzy-match a track by name/role, with disambiguation ('2 drum tracks: which?')
Attacks that exploit this kind of access
Fuzzy-match a track by name/role, with disambiguation ('2 drum tracks: which?'). It is categorised as a Read tool in the Orpheus MCP Server, which means it retrieves data without modifying state.
Register the Orpheus MCP server in PolicyLayer and add a rule for resolve_track: 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 Orpheus. Nothing to install.
resolve_track 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 resolve_track 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_track. 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_track is provided by the Orpheus MCP server (mal0ware/orpheus). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →