Trigger a library scan on the Emby media server.
AI agents invoke emby_scan_library to trigger actions in HomeOps MCP Server. 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.
This tool triggers an active operation (library scan) on an external media server. It doesn't simply read data, nor does it delete or write content — it initiates a scanning process whose side effects (indexing, metadata updates, resource consumption) depend on the server state. This fits the Execute category as it runs an external operation.
From the tool's definition 'Trigger a library scan on the Emby media server' — triggers an external operation on the Emby server
Attacks that exploit this kind of access
Trigger a library scan on the Emby media server. It is categorised as a Execute tool in the HomeOps MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the HomeOps MCP Server MCP server in PolicyLayer and add a rule for emby_scan_library: 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 HomeOps MCP Server. Nothing to install.
emby_scan_library 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 emby_scan_library 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 emby_scan_library. 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.
emby_scan_library is provided by the HomeOps MCP Server MCP server (wolffcatskyy/homeops-mcp). 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 →