io.github.shalevshalit/image-recognition-mcp

Image Recongnition

MCP server for AI-powered image recognition and description using OpenAI vision models.

alive probed 2026-10-14

1tools

123tokens in Claude Opus 5.5

137tokens in Claude Code

<0.1 %of a 200k context window

65o200k_base estimate

327 msto initialize

7 msto list tools

Run it: npx -y image-recognition-mcp@1.0.0 (stdio, probed in a container with the network off)
Host: npmjs.com
Reports itself as: Image Recongnition 1.0.0
Capabilities: tools
Instructions: none
Claude count: Claude Opus 5.5, measured 2026-10-14. Counted again when the tool definitions change. Method.
Repository: https://github.com/mcp-s-ai/image-recognition-mcp
Registry: active, updated 2025-09-10 · registry entry
Reachable: 1 of the last 1 probe

Most expensive tools

Tool	Tokens (o200k)	Share of this server
describe-image	65	100 %

Badge and feed

[![mcpcost](https://mcpcost.ulehla.dev/badge/io.github.shalevshalit/image-recognition-mcp.svg)](https://mcpcost.ulehla.dev/s/io.github.shalevshalit/image-recognition-mcp)

An entry for every probe that changed the result, the tool count or the token cost: Atom feed. Add it to a feed reader or a Slack RSS app to hear when the server stops answering or its tool set grows.