AI agents call reelgrep_video_info 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 performs a straightforward metadata lookup against a local video library index. It retrieves information about a video without creating, modifying, deleting, or executing any operations. The blast radius is minimal—metadata exposure is informational only. All sibling tools (list, search, find, get) reinforce this as a read-only query interface for browsing a local library.
From the tool's definition Tool retrieves 'full metadata for a single indexed video' by file_hash identifier. The verb 'Get' and action of retrieving metadata without modifying data indicates a read-only query operation.
Attacks that exploit this kind of access
Get full metadata for a single indexed video by file_hash (full or 8+ hex prefix). 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_video_info: 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_video_info 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_video_info 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_video_info. 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_video_info 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 →