get_scenes
AI agents call get_scenes to retrieve information from Reka Vision MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to fetch or query scene information from videos without modifying, deleting, or executing operations. No side effects or destructive actions are implied. The empty description lowers confidence slightly, but the consistent naming pattern with other read-only tools on the server and the retrieval-oriented nature of 'get_scenes' clearly indicates a Read category with low severity.
From the tool's definition Tool name 'get_scenes' indicates a retrieval operation. The server context shows this is part of a video analysis platform with tools like 'get_captions', 'get_transcript', 'get_video' which are all read operations.
Attacks that exploit this kind of access
get_scenes. It is categorised as a Read tool in the Reka Vision MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Reka Vision MCP Server MCP server in PolicyLayer and add a rule for get_scenes: 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 Reka Vision MCP Server. Nothing to install.
get_scenes 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 get_scenes 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 get_scenes. 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.
get_scenes is provided by the Reka Vision MCP Server MCP server (reka-ai/reka-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 →