Plugins

The complete directory supports discovery. Quality dimensions are shown separately; automated analysis does not prove feature completeness. The plugin manager continues local inspection.

Found 1065 source candidates (configured-source coverage 15812 / 15812) · snapshot: 2026-09-19Search order: text relevance first + bounded quality evidence

image-mcpTOBYCAI/image-mcpCatalog Analyzed本地 Pillow 图片处理 MCP：12 工具（信息/缩放/裁剪/转换/压缩/旋转/翻转/缩略图/水印/特效/占位/叠加），离线零成本，经 dsh-mcp-client 接入 DSH。Local Pillow image MCP with 12 tools for DeepSeek Harness, offline & free. | Platforms: macOS/Windows/Linux (Python+Pillow)Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 stars dsh-client-paste-imagequei4r/dsh-client-paste-imageCatalog AnalyzedDSH web client plugin: pasted images become file paths on text-only model routes (via dsh-drop-caret's upload route); vision models keep the native pipelineVision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 stars c-visioncczzyy-cn/c-visionCatalog AnalyzedDeepSeek Harness (DSH) 自主视觉Plugin —— 给智能体屏幕/窗口视觉 + 电脑使用能力（see/ocr/list_windows + 鼠标键盘Action），跨语言调用捆绑的 Python cvision，Windows / macOS 可用。Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 stars jolly-dsh-visionJollY-Life/jolly-dsh-visionCatalog AnalyzedModLens 风格的 DeepSeek Harness 视觉桥接Plugin：deepseek-v4-pro 当大脑、deepseek-v4-flash-vision-exp 当眼睛，提供 vision 工具与 (ds vision) 视觉孪生模型，让纯文本模型也能看图、直接贴图。Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 stars vision-mcpweekitmo/vision-mcpCatalog AnalyzedMCP server for image understanding through OpenAI-compatible vision APIs. To provide image recognition capabilities for those large models that do not support Multimodal.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 stars dsh-plugin-visionco-Elly/dsh-plugin-visionCatalog Analyzed👁️ Give your DeepSeek Harness the gift of sight — enables pure-text LLMs to analyze images via Zhipu's free GLM-4V-Flash vision modelVision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 stars dsh-image-amnesiaChoco-Zz/dsh-image-amnesiaCatalog AnalyzedDrop historical images before DeepSeek Harness relay requests; keep native vision on the newest image.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 stars dsh-plugin-vision-bridgelcb522/dsh-plugin-vision-bridgeCatalog AnalyzedDSH plugin: let text-only model sessions see images via a vision-model bridge (chat uploads + read_image)Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 stars dsh-visionariesy/dsh-visionCatalog AnalyzedDeepSeek Harness (DSH) dynamic Cordis plugin: global image upload button + configurable vision-model recognition with fallbackVision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 stars dsh-vision-bridgeShiraGawaAnri/dsh-vision-bridgeCatalog AnalyzedDSH profile Plugin包：当会话使用不支持图片的模型（如 DeepSeek）时，不再弹出 "当前模型不支持图片"之类的拦截，而是调用工具进行视觉识别Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 stars dsh-vision-bridgeshenhuanageshei/dsh-vision-bridgeCatalog AnalyzedDeepSeek Harness plugin - session screenshots route by model capability: inline for vision models, VLM-read for text-only models (tool/auto modes)Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 stars dsh-vision-bridgealaxrpg/dsh-vision-bridgeCatalog AnalyzedAdds image input and recognition through configured DSH providers or an OpenAI-compatible endpoint.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 stars dsh-image-bridgehaitang1/dsh-image-bridgeCatalog Analyzed让文本模型（如 DeepSeek）也能正常发送图片：图片落盘到工作区，消息转成仅模型可见的路径文本，由模型调用视觉/MCP 工具识别。Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 stars xby-wikimedia-search-imagesxby-skill/xby-wikimedia-search-imagesCatalog Analyzed该MCP服务器使AI助手能够在Wikimedia Commons上搜索图片，提供详细的元数据和可选的缩略图组合，帮助AI模型进行视觉比较。Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 stars dsh-vision-relayjunhongchashui/dsh-vision-relayCatalog Analyzed零修改、零切换的 DeepSeek Harness 视觉能力Plugin：纯文本模型粘贴即读图片，云端 + 本地 Ollama 双后端自动切换，ModLens v2 风格结构化证据输出。Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 stars dsh-vision-bridgedoebkblcya/dsh-vision-bridgeCatalog AnalyzedDynamic vision bridge plugin for the DSH Web GUI: pasted images are recognized on demand via Bailian vision models (qwen3-vl-flash / qwen-vl-ocr)Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 stars dsh-plugin-show-imagejusthalfbit/dsh-plugin-show-imageCatalog AnalyzedDeepSeek Harness (DSH) 会话内图片渲染Plugin：全局 show_image 工具 + 点击放大 lightbox。 | Inline image rendering plugin for DSH: global show_image tool + click-to-enlarge lightbox.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 stars dsh-vision-fallback-bridgebaizhichen-web/dsh-vision-fallback-bridgeCatalog AnalyzedLightweight DeepSeek Harness upload bridge: images and common documents become workspace paths so text-only DeepSeek models can read them with Qwen-MM-Plugins vision tools.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 stars

Source candidateDescriptions are untrusted text imported from third-party catalogs and public sources reviewed by the RegistryLocal inspect / plan / confirm is still required before installation