What is upload-image-s3?

Instructions for uploading a local image to storage services such as Amazon S3 or Cloudflare R2 and returning a public web address.

Use them to host an image online, upload it to compatible storage, or obtain a public URL for a local image.

They define how to find the file, upload it, choose its storage path, and avoid overwriting existing files.

upload-image-s3 — Skill for Claude Code by tadeukaiba

Install

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.

Any agent

npx skills add tadeukaiba/mcp-media-toolkit --skill upload-image-s3

Clone the repo

git clone --depth 1 https://github.com/tadeukaiba/mcp-media-toolkit

Made for: Claude Code.

Or install mcp-media-toolkit, the plugin that ships this one along with the rest of its 3 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tadeukaiba/mcp-media-toolkit/upload-image-s3/github.svg)](https://agentmods.dev/skills/tadeukaiba/mcp-media-toolkit/upload-image-s3)

Your own site

<a href="https://agentmods.dev/skills/tadeukaiba/mcp-media-toolkit/upload-image-s3"><img src="https://agentmods.dev/badge/skills/tadeukaiba/mcp-media-toolkit/upload-image-s3/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tadeukaiba/mcp-media-toolkit/upload-image-s3"><img src="https://agentmods.dev/badge/skills/tadeukaiba/mcp-media-toolkit/upload-image-s3.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 752 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00116	$0.00752
Opus 5.5	$0.00046	$0.00301
Sonnet 5.5	$0.00023	$0.00150
Haiku 4.5	$0.00012	$0.00075

Measured 2mo ago against content hash a197594ee357, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

upload-image-s3 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.

skills/upload-image-s3/SKILL.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Upload Image to S3-Compatible Storage

Upload a local image file to the configured S3-compatible storage using the upload_image_s3 MCP tool and return the public URL.

Workflow

Get the file path.
- If the user provided an absolute path, use it directly.
- If they provided a relative path or just a filename, ask for the absolute path or resolve it based on the current context (e.g. recently generated files, files in the current working directory).
- If they referenced "the last image" or "the one we just generated", use the file path from the most recent generate_image_gemini result in this conversation.
Verify the file exists. Before calling the tool, use a quick Bash call (test -f <path>) if there's any doubt — it's cheaper to fail fast with a clear message than to wait for the MCP error.
Decide on a key (optional).
- Default: the tool auto-generates images/<timestamp>-<filename>. Use this unless the user has a reason to override.
- If the user wants a specific path in the bucket (e.g. avatars/user-123.png), pass it as key.
- Keys with slashes work fine — they become folder-like prefixes in the bucket.
Call the tool. Use mcp__mcp-media-toolkit__upload_image_s3 with file_path (and key if overriding).
Report the URL. The tool returns the bucket, key, and public URL. Show the user the public URL prominently — that's what they actually need. Mention the bucket/key only if relevant.

Errors

"S3 storage is not configured" — the user needs to set S3_ENDPOINT, S3_ACCESS_KEY_ID, S3_SECRET_ACCESS_KEY, S3_BUCKET, and S3_PUBLIC_URL in their environment. Point them at the project README's Configuration section.
"File not found" — the path is wrong or the file was deleted. Ask the user to confirm the path.
"S3 upload failed: Access Denied" — the credentials are wrong or the bucket doesn't allow uploads with that key. Tell the user to verify their API token permissions include PutObject on the target bucket.
"S3 upload failed: NoSuchBucket" — the bucket doesn't exist. Tell the user to create it or fix S3_BUCKET.

Read the full file on GitHub · 39 lines

Changes

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 · 39 lines · 116 tokens per session scan A a197594ee357

Subscribe to this mod's changes

upload-image-s3 is a skill published in the GitHub repository tadeukaiba/mcp-media-toolkit (0 stars, last pushed 7mo ago), licensed MIT. It adds 116 tokens to every session and 752 once invoked, about $0.0005 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.

Claude Code Cloud DevOps and cloud agent-skills ai-tools cloudflare-r2 codex cursor

upload-image-s3 next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
upload-image-s3tadeukaiba/mcp-media-toolkit	Skill	0	7mo ago	MIT	A	116	Claude Code
architecture-diagramulises-jeremias/agent-toolkit	Skill	19	yesterday	MIT	A	61	Claude Code
diagnose-domainoborseth/Porkbun-MCP	Skill	36	yesterday	MIT	A	72	Claude Code
change-dns-safelyoborseth/Porkbun-MCP	Skill	36	yesterday	MIT	A	93	Claude Code
publish-websiteoborseth/Porkbun-MCP	Skill	36	yesterday	MIT	A	65	Claude Code
move-dns-to-porkbunoborseth/Porkbun-MCP	Skill	36	yesterday	MIT	A	75	Claude Code
aws-well-architected-reviewulises-jeremias/agent-toolkit	Skill	19	yesterday	MIT	A	55	Claude Code