Iris — Evidence-first image reading for AI agents — metadata, OCR text, regions, and citeable evidence without generative LLM.
Iris — Evidence-first image reading for AI agents — metadata, OCR text, regions, and citeable evidence without generative LLM.
Evidence-first image reading for AI agents. One call turns any local image into an Agent Media Twin — dimensions, metadata, optional OCR with bounding boxes, and trust warnings you can cite without asking a vision LLM to guess.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| read_image | Read a local image and return dimensions, mime, metadata, optional OCR, and trust warnings. |
{
"mcpServers": {
"image-reader-1": {
"command": "npx",
"args": ["-y", "@sylphx/image-reader-mcp"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
Generates both vector and raster images using EverArt's AI models, providing flexible storage and format conversion.
Provides file system operations, analysis, and manipulation through a standardized tool interface.
Document to Markdown MCP server: PDF, Word, PowerPoint, Excel and HTML, with OCR for large files.
A MCP server for BNB Chain that supports BSC, opBNB, Greenfield, and other popular EVM-compatible networks.
A lightweight [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) server that converts documents to Markdown. Supports PDF, DOCX, HTML
Expose the 5dive agent-fleet CLI as Model Context Protocol tools. Point any MCP client (Claude Desktop, Cursor, Cline, or your own) at this stdio server to file tasks, inspect and message agents, and read the fleet…