AI agents call reelgrep_recent_cues to retrieve information from Reelgrep without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves subtitle data within a specified time window. It performs no write, destructive, execute, or financial operations. The scope is limited to reading existing video metadata/subtitles, making it a straightforward Read category tool with low severity risk.
From the tool's definition Tool returns subtitle cues from video around a timestamp - purely retrieves data with 'no side effects'. The description explicitly states it's for 'getting context around a hit', indicating query/retrieval functionality rather than modification or execution.
Attacks that exploit this kind of access
Return subtitle cues from a single video within a +/- window around a timestamp. Useful for getting context around a hit from reelgrep_search_subtitles. It is categorised as a Read tool in the Reelgrep MCP Server, which means it retrieves data without modifying state.
Register the Reelgrep MCP server in PolicyLayer and add a rule for reelgrep_recent_cues: 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 Reelgrep. Nothing to install.
reelgrep_recent_cues 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 reelgrep_recent_cues 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 reelgrep_recent_cues. 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.
reelgrep_recent_cues is provided by the Reelgrep MCP server (solomonneas/reelgrep-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 →