vision-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@vision-mcp analyze ./screenshot.png — does the checkout page look broken?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
vision-mcp
Give a non-vision coding agent (OpenCode, Claude Code, Cursor, Cline, …) the ability to "see" an image — for UI/design review, OCR, "what's on this screenshot", or comparing a render to an expectation — using free OpenRouter vision models.
Zero dependencies. Speaks MCP over stdio. The agent calls one tool:
analyze_image(prompt, image) -> { content, servedModel, attempts, tried }image= local file path or http(s) URL.The server converts everything to base64 (the free nemotron endpoint rejects http image URLs but accepts base64), then calls OpenRouter.
Model chain: several free vision models first (each with retries), then a cheap paid fallback. First model that answers wins; the result says which one served it.
Why
Agents without native vision cannot judge whether a game/UI looks good. Numeric layout checks catch clipping, not beauty. This tool lets the agent itself run a design review on Playwright screenshots before shipping — no need to pick a vision subagent.
Related MCP server: image-viewer-mcp
Models (defaults, override via env)
Free (tried in order, 2 attempts each):
nvidia/nemotron-3.5-super-vl:freegoogle/gemma-4-31b-it:freenvidia/nemotron-3-nano-omni-30b-a3b-reasoning:freegoogle/gemma-4-26b-a4b-it:free
Cheap paid fallback (last resort, 3 attempts):
z-ai/glm-5.3-flash:floor
Free endpoints are rate-limited; the paid fallback guarantees an answer. Check current free models at https://openrouter.ai/models (filter input modality = image, price = 0).
Install
Option A — run from source (simplest)
git clone https://github.com/<you>/vision-mcp
cd vision-mcp
# no npm install needed (zero deps)
export OPENROUTER_API_KEY=sk-or-v1-...
node server.mjsOption B — MCP client config
OpenCode (opencode.json / opencode.jsonc):
{
"mcp": {
"servers": {
"vision": {
"type": "local",
"command": ["node", "/abs/path/to/vision-mcp/server.mjs"],
"environment": {
"OPENROUTER_API_KEY": "sk-or-v1-...",
"VISION_MODELS": "nvidia/nemotron-3.5-super-vl:free,google/gemma-4-31b-it:free",
"VISION_PAID_FALLBACK": "z-ai/glm-5.3-flash:floor"
}
}
}
}
}Claude Desktop / Cursor / Cline use an equivalent mcpServers block (command + env).
See .env.example for all options.
Configuration (environment)
Variable | Default | Meaning |
| — (required) | OpenRouter key |
| nemotron,gemma-31b,… | comma-separated free models, in order |
| (empty) | one cheap paid model tried last |
|
| attempts per free model |
|
| attempts for the paid fallback |
|
| per-attempt timeout |
|
| max input image size |
| (unset) | if set, local reads confined to this dir (+ OS temp) |
|
| API base |
Security
The API key is read only from the environment — never bundled, never logged.
If
VISION_ALLOWED_DIRis unset, the tool can read any local file path (it's a local dev tool). SetVISION_ALLOWED_DIRto sandbox it to a screenshots folder if you want to restrict reads.Images are sent to OpenRouter (the model provider you select). Don't feed secrets/screenshots you wouldn't send to a third party.
Programmatic use (any MCP host)
The tool is standard MCP; the agent writes its own prompt per task (e.g. "harsh design
review: layout, hierarchy, biggest problem, polish 1–5"). A ready-made design-review prompt
lives in the Playgama skill (templates/vision-design-review-prompt.md).
License
MIT — see LICENSE.
Available Tools
1 toolanalyze_imageA
Get a text answer about an image using a vision model chain (free OpenRouter models first, then a cheap paid fallback, with retries). Use it when you cannot see the image yourself: UI/design review, OCR, "what is on this screenshot", comparing a render to an expectation. Pass a local file path or an http(s) URL. YOU write the prompt for your task. Returns { content, servedModel, attempts, tried }.
Inputs: image (required), prompt (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility of misselection. Its purpose—answering an arbitrary prompt about an image via a vision model chain—is stated unambiguously, including accepted inputs (path or URL) and return shape.
analyze_image follows a clean verb_noun snake_case convention, which is ideal. With a single tool there is no broader pattern to demonstrate consistency against, so it can't quite earn a 5.
A single tool is genuinely sufficient here because the free-form prompt parameter makes it general-purpose (OCR, UI review, render comparison). It is narrowly scoped rather than trivial, though one tool offers no room for specialized conveniences like multi-image diffing.
The domain is 'get an answer about an image,' and the tool covers local paths, URLs, retries, and model fallback with diagnostic metadata returned. Minor gaps: no native multi-image/comparison mode and no way to configure or inspect the model chain, but the prompt-driven design lets agents work around these.
Maintenance
Related MCP Connectors
OCR, transcription, file extraction, and image generation for AI agents via MCP.
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
Create images & video from any MCP agent — 17 models, spend limits, one URL.
Image & PDF tools for AI agents: compress, convert, resize, PDF, AI vision, pipeline.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables vision capabilities for any AI model by routing image analysis requests through OpenRouter's vision models. It provides tools to analyze images from URLs, local file paths, or base64 data.2379 npm19MIT
- FlicenseNot gradedqualityCmaintenanceProvides an MCP tool that analyzes images from local paths, URLs, or data URLs via a vision language model, returning structured descriptions (brief, detailed, summary) so text-only LLMs can understand image content.-
- AlicenseAqualityDmaintenanceVision MCP enables text-only agents to understand images through any OpenAI-compatible vision model. It supports local images, URLs, screenshots, documents, charts, and code errors with tools like analyze_image and understand_image.2MIT
- AlicenseNot gradedqualityDmaintenanceEnables MCP-compatible agents to analyze images via NVIDIA NIM vision models, supporting file paths, URLs, or base64 input to return actionable textual descriptions.9 npmMIT