ImageStep MCP server
online · 100% uptimedev.imagestep/mcp·v0.2.1The image pipeline for agents: presets, assets and jobs. Answers with asset ids and stable URLs.
not scanned yet
0 stars
Reviews
Write oneNobody has reviewed ImageStep yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
ImageStep tools
Tool list not cached yet. `describe` through the gateway fetches it live.
How ImageStep compares
Against every graded Media MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 86/100
- higher than 74% of 1,337 Media servers
- Uptime
- 100%
- of our recent checks; the typical remote Media server answers 100%
- Response time
- 319 ms
- faster than 52% of 862 Media servers
Release history: 3 versions in the registry since 2026-10-03, latest 2026-10-26, typically one every 22 days.
Install ImageStep in Claude Code, Cursor or VS Code
claude mcp add --transport http mcp https://mcp.imagestep.dev/mcp
What the publisher says
From the ImageStep repository's README, as published. We do not edit it. Read it on GitHub
ImageStep SDK
The client side of ImageStep, the image step for your automations: generate, edit, remove backgrounds, upscale, convert and read metadata as one reliable step in your code, an n8n workflow or an AI agent.
Everything that runs on your side of the API lives here:
Each directory has its own README. The documentation is at imagestep.dev/docs, and the API reference at imagestep.dev/docs/api.
Quick start
Create an API key at imagestep.dev/keys, then:
npm install imagestepimport { ImageStep } from "imagestep";
const client = new ImageStep({ apiKey: process.env.IMAGESTEP_API_KEY });
const asset = await client.assets.upload("./product.jpg");
const job = await client.ops.removeBg(asset.id, { wait: true });
const [cutout] = await client.jobs.outputs(job);
const [published] = await client.assets.publish(cutout.id);
console.log(published.publicUrl);How this repository works
The code here is exported from ImageStep's main repository, where the API and its clients change together, in one commit. Each commit here is a snapshot of that export, and releases are tagged here: a v* tag publishes every package whose version is not on npm or PyPI yet, with provenance, from this repository's GitHub Actions.
Issues and pull requests are welcome; see CONTRIBUTING.md. To report a vulnerability, see SECURITY.md.
Development
pnpm install # Node 22.19+ for the workspace (the CLI's floor); pnpm is pinned by packageManager
pnpm check # lint + format
pnpm test # every JavaScript package's unit tests
pnpm test:python # the Python SDK's tests (needs uv)License
MIT, see LICENSE. Every package carries its own LICENSE and THIRD-PARTY-NOTICES.md.
Nothing above is checked by us. What we check is on the safety report.
ImageStep: common questions
- Is ImageStep MCP server safe?
- Yes, by our scan: it is graded A (86/100). Read the ImageStep safety report
- How do I install ImageStep?
- It runs remotely at mcp.imagestep.dev. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does ImageStep need an API key?
- Yes. The registry entry asks for
IMAGESTEP_API_KEY,Authorization. - Is ImageStep maintained?
- The last commit was 32 days ago (2026-10-03). The latest release is v0.2.1.
- Is ImageStep up?
- 100% of our last 28 checks got an answer. We check remote servers about four times a day.
- What can I use instead of ImageStep?
- Servers from other publishers that do the same job: three.ws Vision MCP server, Loopcut MCP server and Darkroom MCP server.
- How does ImageStep compare with other Media MCP servers?
- safety score 86/100 (higher than 74% of 1,337 Media servers); uptime 100% (of our recent checks; the typical remote Media server answers 100%); response time 319 ms (faster than 52% of 862 Media servers). Full comparison.
Alternatives to ImageStep
Same job from other publishers: the closest match first, then the best rated.
- three.ws VisionImage understanding for AI agents — analyze and describe any image via the three.ws pipeline.not reviewedEstablishedA
- LoopcutLoopcut's cloud tools for Blender: GPU render, assets, images, 3D models, motion and audio.not reviewedGrowingB
- DarkroomImage processing pipeline for Next.js. Responsive optimization with Sharp.not reviewedGrowingA
- Remove AI WatermarksIdentify and remove AI watermarks and provenance metadata from your own images and video.not reviewedWidely usedA
Transloadit Media ProcessingProcess video, audio, images and documents with Transloadit Robots. Connect by URL with OAuth.not reviewedEstablishedA