About Picture Identification MCP
Picture Identification MCP is an MCP server published by HaoyueQin in the Content category: 本地视觉理解 MCP 服务，为 AI agent 提供识图能力：通过 vision / ocr / list_models / providers 四个 MCP 工具描述截图、界面、图表与照片。.
The repository has 5 stars and 0 forks, with the last commit 2 months ago. Recent commit activity is the strongest signal that reported issues will get attention.
Install
From source
git clone https://github.com/HaoyueQin/picture-identification-MCPThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Ask AI
✦
Ask AI about Picture Identification MCP
Powered by Claude · Grounded in docs
I know everything about Picture Identification MCP. Ask me about installation, configuration, usage, or troubleshooting.
Security checks
6 checks have not been run yet.
Releases
v0.1.3picident v0.1.3 · 8 Aug 2026Full Changelog: https://github.com/HaoyueQin/picture-identification-MCP/compare/v0.1.2...v0.1.3
v0.1.2picident v0.1.2 · 6 Aug 2026Full Changelog: https://github.com/HaoyueQin/picture-identification-MCP/compare/v0.2.1...v0.1.2
v0.2.1picident v0.2.1 · 4 Aug 2026Full Changelog: https://github.com/HaoyueQin/picture-identification-MCP/compare/v0.2.0...v0.2.1
v0.2.0picident v0.2.0 · 4 Aug 2026Full Changelog: https://github.com/HaoyueQin/picture-identification-MCP/compare/v0.1.1...v0.2.0
v0.1.1pic-id v0.1.1 · 3 Aug 2026pic-id v0.1.1 修复与改进 设置页模型选择：模型列表全量返回、取消"是否支持识图"自动筛选（此前的启发式会把文本模型 glm-4.5 误判为视觉模型并自动选中）；添加/编辑表单新增"手动输入模型名"输入框，智谱/DeepSeek/自建网关等无 /models 接口的供应商也能直接配置目标模型。 图片输入压缩：本地文件与 URL 图片长边超过 2048px 自动等比缩放并转 JPEG(q85) 再上传，避免超尺寸截图触发供应商限制（借鉴…