Preview and execute high-confidence ARR manual imports for queue items
AI agents use manual_import to create or update resources in FlixBridge — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your FlixBridge environment.
This tool creates or modifies data (imports media into libraries) which is reversible through deletion or re-organization, placing it in Write rather than Execute or Destructive. The 'preview' capability suggests intentional data changes.
From the tool's definition Tool description states 'execute high-confidence ARR manual imports for queue items'. The term 'execute' combined with 'import' indicates the tool modifies library state by adding/organizing media content.
Attacks that exploit this kind of access
Preview and execute high-confidence ARR manual imports for queue items. It is categorised as a Write tool in the FlixBridge MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the FlixBridge MCP server in PolicyLayer and add a rule for manual_import: 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 FlixBridge. Nothing to install.
manual_import 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 manual_import 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 manual_import. 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.
manual_import is provided by the FlixBridge MCP server (thesammykins/flixbridge). 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 →