AI agents call overseerr_movie_requests to retrieve information from Overseerr without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Although the description is empty, the tool name and server context strongly suggest this retrieves or lists movie requests from Overseerr. The presence of a separate 'overseerr_request_movie_to_library' tool indicates that request *creation* is handled elsewhere, making this tool primarily a retrieval/query operation with no side effects. Low severity as read operations have minimal blast radius.
From the tool's definition Tool name 'overseerr_movie_requests' and sibling tool 'overseerr_tv_requests' appear in a list alongside query operations like 'overseerr_search_media' and 'overseerr_get_users'.
Attacks that exploit this kind of access
overseerr_movie_requests. It is categorised as a Read tool in the Overseerr MCP Server, which means it retrieves data without modifying state.
Register the Overseerr MCP server in PolicyLayer and add a rule for overseerr_movie_requests: 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 Overseerr. Nothing to install.
overseerr_movie_requests 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 overseerr_movie_requests 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 overseerr_movie_requests. 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.
overseerr_movie_requests is provided by the Overseerr MCP server (ptbsare/overseerr-mcp-server). 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 →