Enables optional local semantic object detection via Ollama, allowing the read_image tool to return open-vocabulary objects with bounding boxes and confidence scores.
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., "@Image Reader MCP read this image and extract all text with coordinates"
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.
Iris gives agents deterministic facts from screenshots, UI captures, forms, diagrams, charts, and other images. It returns dimensions, metadata, OCR regions, layout blocks, crops, and trust warnings without requiring a generative vision model.
npx -y @sylphx/irisFor Claude Code:
claude mcp add iris -- npx -y @sylphx/iris{
"path": "/absolute/path/to/screenshot.png",
"include_ocr": true
}The result includes image dimensions, hash, OCR lines with bounding boxes, layout blocks, a text map for agents, and explicit warnings or gaps.
Related MCP server: Vision MCP Server
Ask your agent | Iris returns |
“Read this screenshot.” | text regions and layout facts |
“What changed between these UI captures?” | image diff evidence |
“Extract this form.” | OCR lines and boxes |
“Crop the important region.” | citeable pixel evidence |
“Check the image metadata.” | format, dimensions, EXIF trust warnings |
Tool | Purpose |
| Primary image facts and optional OCR |
| Cheap metadata and geometry probe |
| Extract a citeable pixel region |
| Report pixel and layout differences between two images |
fast returns deterministic metadata, geometry, and layout.
quality explicitly enables OCR and local semantic helpers.
Generative captions and object detection are opt-in and never authoritative.
GPS metadata is redacted unless explicitly requested.
Oversized or unsupported files fail with a structured error.
Every result keeps source path and hash, pixel locators, extraction route, confidence or warnings, and known gaps. OCR and optional model output never replace deterministic geometry.
Product | Job |
PDF answers with page-level proof | |
Video timelines and timestamp evidence | |
Repository architecture and impact | |
Exact code-chunk retrieval | |
Web research with source excerpts |
Each product is independent. Install only the tools your agent needs.
bun install
bun run build
bun test
cargo test
bun run benchmark:public-proof
bun run benchmark:release-gateMIT
This server cannot be deployed
Verified, sourced, real-time intelligence layer for AI agents.
Give agents instant OG image generation, social metadata audits, and rendering guidance.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Give agents eyes on any web page: structured context, and changes explained in plain language.
