Image Reader MCP

io.github.SylphxAIPublished by GitHub account SylphxAIv0.1.0Updated Oct 24, 2026

Evidence-first image MCP. Agent Media Twin with metadata and citeable OCR evidence.

VerifiedSTDIODesktop onlyFiles & StorageMedia & Design

Overview

AI-generated overview

Local stdio MCP server that gives an assistant measured image facts — dimensions, format, metadata, crops and diffs — with optional local Tesseract OCR.

What you can do
  • Read one local image for dimensions, format, metadata and trust warnings, with optional region crop and OCR.
  • Probe an image for format, dimensions, pixel count and source hash without OCR or cropping.
  • Crop a region and return citeable pixel bounds and a hash, optionally with PNG bytes.
  • Compare two same-size images and report changed pixels and a changed box.
  • Return OCR lines with text, bounding box and confidence only when explicitly requested.
When to use it
Useful when an assistant needs verifiable facts about screenshots or images instead of guessing text or size, for example checking a screenshot's dimensions, extracting OCR text with boxes, or diffing two captures of the same UI.
Requirements
Runs locally over stdio, typically via npx with the published npm package; Node.js and network access for the first fetch. No API key. OCR requires the tesseract binary on PATH; without it, reads still succeed but report an OCR gap.
Before you install
It reads local image files by path, so the assistant can access any image path it is given. OCR runs locally and no generative vision model is used. GPS metadata is always redacted with no way to restore it. Files over the default 32 MiB cap or undecodable files fail with an error. The README states the repository is archived and merged into another package.

Installation

In SourceWeft

  1. Open Image Reader MCP in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Merged into anymd (2026-09-25). anymd reads PDFs, Office files, EPUB, web pages, images and video into clean Markdown for AI agents: npx -y @sylphx/anymd. This repository is archived.

[Iris]

Iris

Image facts with pixel-level proof.

Dimensions, format, and metadata by default. Local Tesseract OCR only when requested.

[npm] [license]

npm @sylphx/iris · bin iris · MCP io.github.SylphxAI/iris

The problem

A screenshot is not a paragraph. An agent that guesses the text, the size, or the pixels it never measured will cite something it cannot show.

The difference

The askIris returns
“Read this screenshot.”dimensions, format, metadata, and trust warnings. No OCR unless you ask.
“Read the text.”OCR lines with boxes, only when include_ocr is true or profile is quality.
“What changed between these two captures?”changed pixels and a changed box, when both images are the same size.
“Crop this region.”pixel bounds and a hash. PNG bytes only if include_region_image is true.

Iris does not run a generative vision model. A missing Tesseract binary is a gap, not a made-up transcription.

Install

bash
npx -y @sylphx/iris

That starts a stdio MCP server. No API key. OCR needs the tesseract binary on PATH.

Your clientSetup
Any agent / CLInpx -y @sylphx/iris
Claude Codeclaude mcp add iris -- npx -y @sylphx/iris
Claude Desktop / Cursor / VS Code / Codex"command": "npx", "args": ["-y", "@sylphx/iris"]
json
{  "mcpServers": {    "iris": { "command": "npx", "args": ["-y", "@sylphx/iris"] }  }}

A read, then text only if you ask

json
{ "path": "/absolute/path/to/screenshot.png" }

fast, or no profile, returns dimensions, format, metadata, and trust warnings. It does not run OCR.

json
{  "path": "/absolute/path/to/screenshot.png",  "include_ocr": true}

include_ocr: true, or profile: "quality", runs local Tesseract. Explicit include_ocr: false wins over quality. If Tesseract is missing, status stays ok and gaps includes OCR_UNAVAILABLE.

Reference: tools · defaults

Tools

ToolWhen to call it
read_imageOne local image. Geometry and metadata. OCR only when requested. An optional region crops inside this read.
image_probeFormat, dimensions, pixel count, and source hash. No OCR and no crop.
crop_regionOne citeable region: bounds and hash. Set include_region_image for PNG bytes. No OCR.
compare_imagesChanged pixels between two images of equal dimensions. No OCR.

What it will not pretend

  • GPS fields are always redacted. There is no switch that puts them back.
  • The default file cap is 32 MiB (33,554,432 bytes). A cropped region may not exceed 67,108,864 pixels.
  • compare_images requires equal dimensions. It does not resize either image.
  • OCR lines are {text, bbox, confidence}. The default language is eng.
  • Oversized or undecodable files fail with an error. They are not returned as a successful read.

Companion MCP tools

ProductJob
CitraPDF answers with page-level proof
CueVideo timelines and timestamp evidence
SpineRepository architecture and impact
LocusExact code-chunk retrieval
LookoutWeb research with source excerpts

Each product is independent. Install only the tools your agent needs.

Documentation

Websitesylphxai.github.io/iris
QuickstartInstall and first call
CompareWhat Iris does, and what it refuses

Development

bash
bun installbun testbun run checkbun run docs:buildcargo test

License

MIT

Source: README.md at commit 90fb41a

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts