screenshot-feedback-hook-mcp
Cross-platform screenshot feedback tool and DSH bundle that feeds visual captures directly to AI agents.
Install
$ dsh plugin --profile web add dsh-screenshot-feedback-hook-mcpPlugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Captures full multi-monitor or single-monitor screenshots with downsampling and iterative JPEG compression
- Integrates natively as a DeepSeek Harness bundle via Cordis patches without manual YAML patching
- Stores captures in DSH persistent attachments and passes them automatically as image blocks to vision-capable models
- Provides MCP server endpoints and CLI hooks for automated stop or post-tool triggers
Useful For
- Providing automated visual feedback loops for AI agents building frontend web pages or UI components
- Enabling agents to inspect EDA, CAD, or desktop graphic renderings for self-correction
- Automated capture upon round completion or file edit triggers
Who It Fits
- DeepSeek Harness users working with vision-capable models
- Developers configuring autonomous coding agents needing visual verification
- Engineers building UI or CAD automation workflows
Documented Limitations
- Requires a vision-capable model with image modality configured; text-only models like standard deepseek-v4 cannot consume the screenshot image blocks
- Wayland environments on Linux have limited support compared to X11
- Requires DeepSeek Harness >= v0.1.0-rc.8, pnpm, and Python dependencies
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
GitHub reports the repository license as MIT.
No root package.json was captured in the latest GitHub snapshot.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- lkh081231/screenshot-feedback-hook-mcp
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin Bundle
- Source checked
- 79935c0 · 2026-10-21
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 5GitHub stars
- Forks
- 1
- Open issues
- 0
- Last commit
- 2026-08-31
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
DeepSeek Harness-native vision toolkit enabling image Q&A, OCR, UI restoration, grounding, and pixel diff for text-only models.
View plugin →Vision routing and pixel-level tools for text-only DeepSeek Harness agents with built-in free fallback.
View plugin →Automates invoice retrieval from IMAP mailboxes, OCR extraction, categorization, and Excel summary report generation.
View plugin →DeepSeek Harness integration for ego-lite Chromium browser, providing 33 structured automation tools and a real-time visual watch panel.
View plugin →