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 agentmods add skills/runapi-ai/mcp/media-generatornpx skills add runapi-ai/mcp --skill media-generatorgit clone --depth 1 https://github.com/runapi-ai/mcpWrote 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/runapi-ai/mcp/media-generator)<a href="https://agentmods.dev/skills/runapi-ai/mcp/media-generator"><img src="https://agentmods.dev/badge/skills/runapi-ai/mcp/media-generator.svg" alt="Measured on agentmods" 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 | $0.00090 | $0.00492 |
| Opus 5 | $0.00045 | $0.00246 |
| Sonnet 5 | $0.00018 | $0.00098 |
| Haiku 4.5 | $0.00009 | $0.00049 |
Grade A, and why
RunAPI Media Generator 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 4d 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
RunAPI Media Generator
Use RunAPI tools to turn a media request into a validated task.
Workflow
- Identify the modality and likely action.
- Call
mcp__runapi__list_modelswith the narrowest useful filter. - Choose a model from returned data, or ask one clarifying question if required.
- Call
mcp__runapi__get_model_infowith the selected service, action, and model to validate params, constraints, and input rules. - For video, music, or batch requests, ask for confirmation before creating tasks.
- Generate one new opaque idempotency key for the logical task and retain it with the exact service, action, model, and params.
- Delegate creation and the idempotency key to
task-executor, or callmcp__runapi__create_taskdirectly when delegation is unavailable. - Present task ID, status, output URLs, and cost fields when available.
- Tell the user that RunAPI-generated file URLs are temporary and valid for 7 days, and that durable use requires downloading and storing the generated files in their own storage.
Rules
- Do not invent model slugs.
- Do not hardcode prices.
- Do not derive the idempotency key from a JSON-RPC request ID or
X-Client-Request-Id. - Do not retry task creation automatically when its result is unknown. An explicit retry must reuse the original key with identical input.
- Do not describe generated media as if you inspected it.
- Use
wait=falsewhen the user asks to submit only. - Use
mcp__runapi__get_taskfor follow-up status checks. - For app/backend integrations, include a storage step for generated images, videos, audio, or other files before treating the workflow as production-ready.
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.
- 4d ago First seen · 38 lines · 90 tokens per session scan A 77f4981d5ee0
RunAPI Media Generator is a skill published in the GitHub repository runapi-ai/mcp (55 stars, last pushed 10d ago), licensed Apache-2.0. It adds 90 tokens to every session and 492 once invoked, about $0.0005 per session on Opus 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 2026-08-30.
Other skills, from other repositories
clone-video-ad-seedance-arcads-mcp
Clone an existing video ad onto a new product using Seedance 2.0 through the optional Arcads MCP server. Analyzes the source with arcadsanalyzemedia, adapts its structure, generates via arcadsgeneratevideoseedance20, and polls with arcadswatchasset. Use only when the user explicitly requests Arcads MCP or has selected…
ad-agent-orchestrator
Orchestrates human-approved, end-to-end Meta ad campaigns from competitor research through test concepts, Arcads image/video generation or cloning, human ad copy, PAUSED deployment, explicit activation, and threshold-based performance review. Applies when a user asks to build, launch, test, or iterate a complete…
claymation-ad-arcads-mcp
Produce an Aardman/Laika-style stop-motion claymation video ad end-to-end through the optional Arcads MCP server: gpt-image-2 storyboards, Seedance 2.0 animation, Arcads TTS, stitching, and subtitles. Use only when the user explicitly requests Arcads MCP or has selected MCP transport and the tools are available in the…
pixar-style-ad-arcads-mcp
Produce a Disney-Pixar-style 3D animated video ad end-to-end through the optional Arcads MCP server: gpt-image-2 storyboards, Seedance 2.0 animation, Arcads TTS, stitching, and subtitles. Use only when the user explicitly requests Arcads MCP or has selected MCP transport and the tools are available in the current…
meta-ad-builder
Research, prepare, and deploy finished creatives to Meta (Facebook/Instagram) through the Marketing API. Lists destinations, optionally creates PAUSED campaign structure, uploads images or videos, creates multi-copy TEXTLIQUIDITY ads in PAUSED state, records lineage, and hands deployed IDs to the read-only performance…
arcads-mcp
Create and retrieve AI images, videos, and audio through the optional Arcads MCP server (no .env, no curl, no presigned-upload scripts) — Nano Banana / gpt-image / Seedream / Grok images, Seedance 2.0 / Sora 2 / Veo 3.1 / Kling / Grok videos, TTS, talking-head actors, and media editing (stitch, trim, subtitles…