MCP server for image analysis using OpenRouter
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"wojons-mcp-openvision","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# MCP OpenVision [](https://github.com/Nazruden/mcp-openvision/actions/workflows/ci.yml) [](https://pypi.org/project/mcp-openvision/) [](https://pypi.org/project/mcp-openvision/) [](https://pypi.org/project/wojons-mcp-openvision/) [](https://pypi.org/project/wojons-mcp-openvision/) [](https://opensource.org/licenses/MIT) [](https://buymeacoffee.com/nazruden) [](https://smithery.ai/server/@Nazruden/mcp-openvision) ## Overview MCP OpenVision is a Model Context Protocol (MCP) server that provides image analysis capabilities powered by OpenRouter vision models. It enables AI assistants to analyze images via a simple interface within the MCP ecosystem. ## Installation ### Installing via Smithery To install mcp-openvision for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@Nazruden/mcp-openvision): ```bash npx -y @smithery/cli install @Nazruden/mcp-openvision --client claude ``` ### Using pip ```bash pip install mcp-openvision ``` ### Using UV (recommended) ```bash uv pip install mcp-openvision ``` ### Installing this fork (PyPI) This repository is a maintained fork published under the distribution name "wojons-mcp-openvision". ```bash pip install wojons-mcp-openvision # or uv pip install wojons-mcp-openvision ``` ## Configuration MCP OpenVision requires an OpenRouter API key and can be configured through environment variables: …
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.