Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add lonzzi/tmdb-mcp-server --skill tmdb-mcp-servergit clone --depth 1 https://github.com/lonzzi/tmdb-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lonzzi/tmdb-mcp-server/tmdb-mcp-server)<a href="https://agentmods.dev/skills/lonzzi/tmdb-mcp-server/tmdb-mcp-server"><img src="https://agentmods.dev/badge/skills/lonzzi/tmdb-mcp-server/tmdb-mcp-server/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lonzzi/tmdb-mcp-server/tmdb-mcp-server"><img src="https://agentmods.dev/badge/skills/lonzzi/tmdb-mcp-server/tmdb-mcp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00078 | $0.00518 |
| Opus 5.5 | $0.00031 | $0.00207 |
| Sonnet 5.5 | $0.00016 | $0.00104 |
| Haiku 4.5 | $0.00008 | $0.00052 |
Grade A, and why
tmdb-mcp-server scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
TMDB MCP Server
Overview
Use TMDB MCP tools to search movies, TV shows, and people, then fetch detailed metadata and trending lists with optional language and region localization.
Quick Start
- Clarify the target: movie, TV show, or person. If unclear, search both movies and TV shows.
- Run the relevant search tool with
queryand optionallanguage/region. - Present top matches with
id, title/name, year, and a short overview. - Ask the user to confirm the exact match, then fetch details by ID.
- Provide a concise summary plus the TMDB link returned by the tool.
Task Guide
Search Movies
Use search_movies with query and optional language/region. When results are ambiguous, show 3 to 5 candidates with year and ID and ask which one to open.
Search TV Shows
Use search_tv_shows with query and optional language. If the user provides a year or country hint, use it to rank or filter results in your response.
Get Movie or TV Details
Use get_movie_details or get_tv_show_details after the user confirms the exact title. Summarize key fields:
- Movies: release date, runtime, genres, budget, revenue, overview.
- TV: first air date, seasons count, episodes count, genres, overview.
Trending
Use get_trending_movies or get_trending_tv with timeWindow set to day or week. Share the top results with titles, year, and short overviews, then offer to open details for any item.
Search People
Use search_person for actors, directors, or crew. If the user wants filmography or specific credits, offer to look up the titles they name and fetch details by ID.
Output Conventions
- Always include the TMDB ID when presenting multiple matches.
- Prefer localized titles/overviews when
languageis provided. - Do not guess details; rely on tool output.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 49 lines · 78 tokens per session scan A 72f7813d4235
tmdb-mcp-server is a skill published in the GitHub repository lonzzi/tmdb-mcp-server (1 stars, last pushed 9mo ago), licensed MIT. It adds 78 tokens to every session and 518 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
tmdb-mcp-server compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tmdb-mcp-serverlonzzi/tmdb-mcp-server | Skill | 1 | 9mo ago | MIT | A | 78 | Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |