vision-augment
Uses local Ollama vision-language models (e.g., llava, qwen2.5-vl) as a fallback or primary vision channel, enabling OCR and image reasoning without an external API key.
Routes vision reasoning tasks through OpenAI-compatible API endpoints, allowing the MCP server to use any compatible vision model service for image understanding and question answering.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@vision-augmentDescribe this image in detail: /tmp/photo.jpg"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
vision-augment
本地优先的多模态视觉 MCP —— 为无视觉 LLM(DeepSeek、GLM 等)提供可自定义端点的看图 / OCR / 文档解析能力。
简化配置、本地优先:不强制依赖云端;OCR 与文档解析全部本地完成
视觉理解用视觉模型:OpenAI 兼容通道链,按序降级,最后兜底本地 Ollama VL(无 key 即用)
不限制模型渠道:任意 OpenAI 兼容端点,
base_url + api_key + model三元组可配多个uvx 一键分发:
uvx vision-augment直接接入任意 MCP harness
架构
MCP client (Hermes / Claude / OpenCode ...)
└─ mcp_vision_augment_vision(task_type=reasoning|ocr|document)
└─ Router ─┬─ reasoning → OpenAI 兼容通道链 + Ollama 兜底
├─ ocr → RapidOCR(本地)→ PaddleOCR(可选升级)
└─ document → markitdown(本地)→ PaddleOCR-VL / MinerU(可选升级)所有工具返回统一 JSON envelope:{task_type, tool_used, code, error, result, confidence, metadata},错误码 0-5。
Related MCP server: vision-bridge-mcp
快速开始
环境要求:Python >= 3.12,uv。
方式一:无 key,本地 Ollama(默认)
ollama pull llava # 或任一视觉模型(llava/vision/qwen2.5-vl/...)
uvx vision-augment方式二:自定义 OpenAI 兼容端点(推荐)
uvx vision-augment[ocr,document] # 按需安装本地 OCR/文档引擎# 注册到 Hermes config.yaml(其他客户端见下)
mcp_servers:
vision-augment:
command: uvx
args: [vision-augment]
env:
VISION_AUGMENT_CHANNELS: '[{"base_url": "https://api.example.com/v1", "api_key": "${API_KEY}", "model": "qwen3.7-plus"}]'无通道配置时自动探测本地 Ollama VL 模型作为兜底;通道配置优先。
方式三:从 GitHub 直接安装(未发布到 PyPI 前)
# 最新 master(PEP 508 语法:extras 在 @ 之前)
uvx "vision-augment[ocr,document] @ git+https://github.com/CaoMeiYouRen/vision-augment"
# 锁定 tag / commit
uvx "vision-augment @ git+https://github.com/CaoMeiYouRen/vision-augment@v0.1.0"
# 长期安装到 PATH(等价 pipx)
uv tool install "vision-augment[ocr] @ git+https://github.com/CaoMeiYouRen/vision-augment"方式四:HTTP 传输(streamable-http)
适合 Docker 部署、远程服务器、多客户端并发场景(stdio 单进程只能服务一个客户端):
VISION_AUGMENT_TRANSPORT=streamable-http VISION_AUGMENT_PORT=8000 uvx vision-augment默认绑定
127.0.0.1:8000,MCP 端点/mcp;SDK 对 localhost 自动启用 DNS rebinding 防护跨机器访问:设置
VISION_AUGMENT_HOST=0.0.0.0,并自行加反向代理/鉴权(远程暴露是部署方责任)客户端配置示例(Hermes):
mcp_servers:
vision-augment:
url: http://127.0.0.1:8000/mcp
transport: streamable-http注意:不要给
streamable-http端点发送空params的 initialize 探测请求——SDK 会挂起该请求,用合法握手载荷探测。
注册到其他客户端
// Claude Desktop: claude_desktop_config.json
{ "mcpServers": { "vision-augment": { "command": "uvx", "args": ["vision-augment"] } } }// OpenCode: opencode.json
{ "mcp": { "vision-augment": { "type": "local", "command": ["uvx", "vision-augment"], "enabled": true } } }工具
工具 | 说明 |
| 入口: |
| 环境探测:通道/Ollama/OCR/文档引擎配置状态(不含密钥),供 agent 反馈缺失配置 |
| 清除本地结果缓存 |
安装与使用 Skill
仓库根目录的 SKILL.md 符合 Agent Skills 规范,可通过 npx skills 生态一键安装(需仓库已公开):
# 全局安装到 opencode / hermes-agent
npx skills add CaoMeiYouRen/vision-augment -g -a opencode -a hermes-agent -y
# 或项目级安装(不指定 -g)
npx skills add CaoMeiYouRen/vision-augment
# 查看已安装
npx skills listSkill 安装后 agent 的工作方式:
环境探测:优先调用
mcp_vision_augment_health检查通道/Ollama/引擎状态,自动向你反馈还缺哪些配置及安装命令(如uvx vision-augment[ocr])任务路由:看图 →
reasoning;图片文字 →ocr;文档解析 →document,由 skill 指引 agent 选择故障闭环:错误码 0-5 对应的处置路径写在 SKILL.md 中
手动安装:把 SKILL.md 复制到 ~/.config/opencode/skills/vision-augment/(opencode)或 ~/.hermes/skills/(Hermes)等目录即可。
配置(环境变量,均有默认值)
变量 | 默认 | 说明 |
|
| OpenAI 兼容通道 JSON 数组 |
|
| 本地 Ollama 地址 |
|
| 缓存 TTL(0=关闭) |
|
| 缓存目录 |
|
| 输入大小上限 |
|
| 输出截断上限 |
|
| 允许 http(s) 输入(防 SSRF,默认关闭) |
|
| DEBUG 日志 |
|
| 传输方式: |
|
| HTTP 绑定地址 |
|
| HTTP 端口 |
完整说明见 docs/design.md。
开发
uv sync # 安装开发环境(基础依赖)
uv run pytest # 单元测试(不依赖重型引擎)
uv run ruff check # 代码检查安装可选引擎做集成验证:
uv sync --extra ocr --extra document # RapidOCR + markitdown
# 或全量:uv sync --all-extras(含 PaddleOCR,体积大)发布(CI 自动)
push 到 master 后,release workflow 由 python-semantic-release 根据 conventional commits 自动版本化(pyproject + __version__ + CHANGELOG + tag + GitHub Release),并通过 Trusted Publisher(OIDC,免 token) 发布到 PyPI。
Trusted Publisher 配置(PyPI → Publishing → Trusted Publishers → Add pending publisher):
字段 | 值 |
PyPI Project Name |
|
Owner |
|
Repository name |
|
Workflow name |
|
Environment name | 留空 |
首次发布后 uvx vision-augment 即生效。手动发布备选:uv build && uv publish(需 UV_PUBLISH_TOKEN)。
文档
许可证
MIT © 2026 CaoMeiYouRen
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityBmaintenanceLocal MCP server that provides multi-modal vision capabilities to single-modal base models via API, supporting multi-turn iterative image recognition and document image parsing.5Apache 2.0
- AlicenseAqualityBmaintenanceEnables non-multimodal models to see images by providing MCP tools for image understanding and OCR, backed by any OpenAI-compatible vision model.2MIT
- Alicense-qualityCmaintenanceEnables text-only models to understand images through a conversational MCP server, supporting multi-turn follow-ups, URL inputs, and OpenAI-compatible vision APIs.1MIT
- Alicense-qualityCmaintenanceAdds image recognition and UI grounding capabilities to text-only LLMs through MCP tools, supporting local and cloud vision backends.63MIT
Related MCP Connectors
OCR, transcription, file extraction, and image generation for AI agents via MCP.
User-owned memory for AI agents, Copilot, Claude, IDEs, CLIs, and chat apps over remote MCP.
Multimodal video analysis MCP — transcription, vision, and OCR for any video URL.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/CaoMeiYouRen/vision-augment'
If you have feedback or need assistance with the MCP directory API, please join our Discord server