Iris runs on your own machine — the client starts it, so there is no endpoint to ping. 73 installs a week from npm. Last commit 25 Sep 2026.
Iris — image facts with pixel-level proof. OCR runs only when requested.
The author archived this repository on GitHub, meaning it is no longer maintained.
We read the source, 22 h ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const result = spawnSync(binary, [], {
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add iris -- npx -y @sylphx/iris
{
"mcpServers": {
"iris": {
"command": "npx",
"args": [
"-y",
"@sylphx/iris"
]
}
}
}
[mcp_servers.iris]
command = "npx"
args = ["-y", "@sylphx/iris"]
{
"mcpServers": {
"iris": {
"command": "npx",
"args": [
"-y",
"@sylphx/iris"
]
}
}
}
{
"servers": {
"iris": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@sylphx/iris"
]
}
}
}
OCR text from image URLs, 30 languages, lines with boxes. One flat row per image. Billed on text.
Invoice and receipt extractor: reads PDF and image invoices/receipts with AI, pulling date…
OCR text from images, screenshots and scanned PDFs in 41 languages, with line positions.
PDF, DOCX and image URLs to clean, LLM-ready Markdown or text, with OCR for scanned pages.
Extract local PDF text with page-level paragraphs and English/German OCR fallback.
Audio, captions, PDF extraction, image OCR and LLM APIs with capped USDC payments.
Answer questions over large PDF folders up to 3x faster, with file and page citations. Runs locally.
Fill fillable PDF forms, then prove every value is visible on the rendered page.
Answers built from our own checks of this server.