Verify Roku Ad Framework (RAF) integration. Checks: 1. Manifest: bs_const=RAF_ENABLED=True, bs_libs_required=roku_ads_lib 2. Log analysis: [AdManager] output, ad beacon/impression events, adCompleted/adSkipped/adError states Roku certification requires: - All ads served via RAF (no custom ad impl...
AI agents call roku_check_raf to retrieve information from Roku MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
roku_check_raf inspects and validates RAF configuration by reading manifest settings and analyzing logs. It retrieves information about ad framework integration state and certification compliance status but does not modify any data, execute code on the device, delete resources, or trigger financial transactions. The tool's purpose is diagnostic verification, which is characteristic of Read operations.
From the tool's definition Tool performs verification and analysis activities: 'Verify Roku Ad Framework (RAF) integration', 'Manifest: bs_const=RAF_ENABLED=True', 'Log analysis: [AdManager] output', 'ad beacon/impression events'.
Attacks that exploit this kind of access
Verify Roku Ad Framework (RAF) integration. Checks: 1. Manifest: bs_const=RAF_ENABLED=True, bs_libs_required=roku_ads_lib 2. Log analysis: [AdManager] output, ad beacon/impression events, adCompleted/adSkipped/adError states Roku certification requires: - All ads served via RAF (no custom ad implementations) - All ad beacons fired client-side by RAF - Roku Advertising Watermark applied - enableAdMeasurements() called for US store - setContentGenre/setContentId/setContentLength provided Ref: developer.roku.com/docs/developer-program/advertising/roku-advertising-framework.md. It is categorised as a Read tool in the Roku MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Roku MCP Server MCP server in PolicyLayer and add a rule for roku_check_raf: 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 Roku MCP Server. Nothing to install.
roku_check_raf 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 roku_check_raf 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 roku_check_raf. 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.
roku_check_raf is provided by the Roku MCP Server MCP server (maskelog/roku-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 →