DeepSeek Visionary MCP
A community MCP server that integrates DeepSeek's official multimodal vision model into AI agents. It enables image recognition and OCR capabilities by automating browser login via CDP, allowing agents in hosts like Zed, Cursor, and Claude Desktop to 'see' images without requiring API keys or manual token management.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
What you can do with it
- Enable image recognition for AI agents in MCP-compatible hosts
- Perform OCR on images via browser automation
- Allow agents to view screenshots or uploaded images
Source and maintenance
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
https://github.com/xlight/deepseek-visionary/releases/download/v0.2.2/visionary-server-aarch64-apple-darwin.mcpb
{
"transport": "stdio",
"fileSha256": "517579bd972ac182a30964e5676db9b61c5438422e4a6a21d2bedd9a63860165",
"identifier": "https://github.com/xlight/deepseek-visionary/releases/download/v0.2.2/visionary-server-aarch64-apple-darwin.mcpb",
"registryType": "mcpb"
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Let your agent find its tools
Find servers like DeepSeek Visionary MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.