discover_shows
AI agents call discover_shows to retrieve information from Tv Recommender without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
page | number | — | 页码，默认为1 |
sort_by | string | — | 排序方式，如"popularity.desc" |
with_genres | array | — | 类型数组，如["喜剧", "科幻"] |
with_keywords | array | — | 关键词数组，如["机器人", "太空"] |
with_networks | array | — | 电视网络ID数组，如[213]表示Netflix |
vote_average_gte | number | — | 最低评分，如8.0 |
first_air_date_year | number | — | 首播年份，如2022 |
with_original_language | string | — | 原始语言，如"en"表示英语 |
Parameters from the server's own tool schema.
The tool appears to query or retrieve TV show data based on the discovery pattern established by other read-only recommendation tools on the same server. Without side effects or data modification capabilities, this is classified as Read with low severity (benign information retrieval).
From the tool's definition Tool name 'discover_shows' suggests retrieval/discovery of show data. Empty description limits certainty, but context from sibling tools (find_shows_by_actor, get_popular_shows, get_recommendations_by_genre, get_show_details, etc.) shows this server…
Attacks that exploit this kind of access
discover_shows. It is categorised as a Read tool in the Tv Recommender MCP Server, which means it retrieves data without modifying state.
discover_shows accepts 8 parameters: page, sort_by, with_genres, with_keywords, with_networks, vote_average_gte, first_air_date_year, with_original_language. The full parameter table on this page comes from the server's own tool schema.
Register the Tv Recommender MCP server in PolicyLayer and add a rule for discover_shows: 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 Tv Recommender. Nothing to install.
discover_shows 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 discover_shows 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 discover_shows. 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.
discover_shows is provided by the Tv Recommender MCP server (tv-recommender-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 →