Skip to main content
Glama
TMDB MCP Server

TMDB MCP Server

Get TV recommendations

get_tv_recommendations
Read-only

Retrieve TV shows TMDB recommends for a given show id, using co-viewing and personalization data to find thematically related titles. Use it to discover what viewers of a show also watched.

Instructions

Get TV shows TMDB recommends for the given show id, based on co-viewing/personalization data (what users who liked this also liked), usually the more thematically relevant list. Prefer this over get_similar by default; get_similar matches on shared genres/keywords, a blunter heuristic that can surface tonally unrelated titles. Get the id from search_tv.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "id": "<id>"
    },
    "name": "get_tv_recommendations"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesTMDB TV show id (from search_tv).
pageNo1-based page number for pagination (TMDB returns up to 20 results per page, max 500). Adult/softcore titles are dropped from this list, so a page can come back shorter, even empty, while total_pages/total_results stay TMDB's own; keep paging up to total_pages.

Output Schema

NameRequiredDescriptionDefault
pageYes
resultsYes
total_pagesYes
total_resultsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.15.0
    • changedInput schema / properties / id / description
      Previous value: -"TMDB numeric id."New value: +"TMDB TV show id (from search_tv)."
    • changedInput schema / properties / page / description
      Previous value: -"1-based page number for pagination (TMDB returns up to 20 results per page, max 500)."New value: +"1-based page number for pagination (TMDB returns up to 20 results per page, max 500). Adult/softcore titles are dropped from this list, so a page can come back shorter, even empty, while total_pages/total_results stay TMDB's own; keep paging up to total_pages."
  2. Changed11 schema fields changedv0.14.0
    • removedOutput schema / properties / results / items / properties / overview / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / results / items / properties / overview / type
      Added value: +[
      +  "string",
      +  "null"
      +]
    • removedOutput schema / properties / results / items / properties / poster_url / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / results / items / properties / poster_url / type
      Added value: +[
      +  "string",
      +  "null"
      +]
    • removedOutput schema / properties / results / items / properties / vote_average / anyOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / results / items / properties / vote_average / description
      Added value: +"TMDB's own 0-10 user score. A different audience and scale from the IMDb/RT/Metacritic scores get_movie/get_tv return as `ratings` — don't compare, average or substitute across the two."
    • addedOutput schema / properties / results / items / properties / vote_average / type
      Added value: +[
      +  "number",
      +  "null"
      +]
    • removedOutput schema / properties / results / items / properties / vote_count / anyOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / results / items / properties / vote_count / type
      Added value: +[
      +  "number",
      +  "null"
      +]
    • removedOutput schema / properties / results / items / properties / year / anyOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / results / items / properties / year / type
      Added value: +[
      +  "number",
      +  "null"
      +]
  3. Addedv0.10.1
  4. Removedv0.8.1
  5. Addedv0.8.1
  6. Removedv0.8.0
  7. First observedv0.3.0

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered by structured data. The description still adds genuine behavioral context by explaining that results derive from co-viewing/personalization signals and are tuned for thematic relevance, which tells the agent what kind of output to expect. It does not mention the adult-title filtering or pagination truncation, but the schema carries that.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with the primary action and its data basis, then the routing rule, then the id prerequisite. No filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no explanation, and the pagination edge cases are handled in the schema. For a two-parameter read tool, the description plus structured fields leave nothing an agent needs missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the schema already documents both id (including its search_tv provenance) and page semantics in detail, so the description adds little beyond it. The 'Get the id from search_tv' line duplicates what the schema's id description already states. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Get TV shows TMDB recommends for the given show id') and immediately characterizes the underlying data source (co-viewing/personalization), which separates it from the sibling get_similar by name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives an explicit default recommendation ('Prefer this over get_similar by default') together with the condition that selects the alternative ('get_similar matches on shared genres/keywords'), plus a pointer to search_tv for id acquisition. When-to-use, when-to-prefer-something-else, and prerequisites are all present.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.