GOU-GEE/deepseek-vision
deepseek-vision is a tool for DeepSeek Harness. This repository does not yet provide a project description.
REVIEW SCORECARD
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
Well-engineered MCP plugin giving text-only DeepSeek vision via third-party VL APIs; install if you accept sending image
README shows CI and Publish GitHub Actions badges, PyPI/npm packaging, a pnpm-based plugin with npm test, and verification scripts (verify_install.py, verify_dsh_plugin.py) exercising MCP stdio handshake and tool registration.
README explicitly warns that images are sent to third-party vision APIs, instructs users not to share plaintext keys with AI assistants, and relies on DSH credential storage rather than committing secrets, though the generic MCP config example still shows VISION_API_KEY in plaintext env.
It solves a concrete, common limitation by exposing an analyze_image MCP tool plus a Skill file so text-only DeepSeek models can automatically process images via GLM/Qwen VL backends.
Last updated 2026-08-26, not archived, with active CI/publish workflows and versioned releases (0.4.2) published to both PyPI and npm.
The README is extensive with copy-paste install prompts, per-platform commands, API key guidance, and a privacy note, but the repository description is empty and the install command is listed as unknown, and the excerpt is truncated mid-sentence.
Generated by AI after reading the project README — a decision aid, not an endorsement. Neutral scores are given when information is limited.
Loading GitHub README...
The GitHub README is temporarily unavailable. Please try again later.
Open repositoryPROJECT TOPICS
VALIDATION LADDER
FAQ
This repository does not yet provide a project description.
deepseek-vision has 5 stars and 2 forks on GitHub, last updated 2026-08-26.
deepseek-vision is distributed under the MIT license.
deepseek-vision is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.
CLASSIFICATION EVIDENCE
The system checks GitHub Topics against the site taxonomy and keyword rules. Current matches:image-analysis、mcp、multimodal、ocr、vision、vision-mcp。
liustack
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | The strongest vision add-on plugin for DeepSeek Harness, adding vision capability to text-only models like DeepSeek and GLM, paste an image and get structured JSON evidence (OCR, layout, semantics).
tong-io
TongFlow — Multimodal GenAI Studio
Anionex
[dsh] A more powerful visual toolkit for text-only models: one-line install and use, paste images for direct recognition, multi-image Q&A, screenshot-to-frontend UI restoration, and more｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.
DDDMUC
Free web search provider for DeepSeek Harness - DuckDuckGo backend, no API key needed
anysearch-team
AnySearch web search provider and advanced search tools for DeepSeek Harness (DSH)
omdsh-dev
Connect DSH to your database for conversational data analysis and actionable business insights.