get_captions
AI agents call get_captions 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.
This tool retrieves captions associated with videos, which is a non-destructive read operation with no side effects. The 'get_' prefix and parallel naming with other retrieval tools (get_transcript, get_video, get_scenes) confirm it queries existing data. Confidence is slightly reduced due to empty tool description, but context from sibling tools and server purpose strongly supports this classification.
From the tool's definition Tool name 'get_captions' and sibling tools like 'get_transcript', 'get_video', 'get_scenes' pattern indicate data retrieval operations. The server description mentions 'extraction of transcripts and captions' as supported read operations.
Attacks that exploit this kind of access
get_captions. 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_captions: 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_captions 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_captions 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_captions. 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_captions 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 →