Local Vision MCP (Yuhang-uestc/deepvision-local-mcp) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 12 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
C
Emerging
74/100
4 days ago

Local Vision MCP

Provides local image understanding for text-only LLMs with tools for image analysis, OCR, object detection, and cropping, all processed on-device.

→ Yuhang-uestc/deepvision-local-mcp· listed on glama

Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

Yuhang-uestc

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

Glama

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
✅
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configOLLAMA_HOSTOllama 服务地址；可写裸主机/端口（如 0.0.0.0、127.0.0.1:11434），自动补全协议与端口
configOLLAMA_VISION_MODEL默认视觉模型
configVISION_MODEL_QUICK快速模式模型（未安装自动回退 8B）
configLOCAL_VISION_MAX_MB单张图片大小上限（MB）
configLOCAL_VISION_CACHE第二次调用秒回，不用重复等本地模型推理。可用 =0 关闭。
configLOCAL_VISION_CACHE_TTL缓存有效期（秒）
configLOCAL_VISION_CACHE_MAX缓存最大条数（超出淘汰最旧）
configLOCAL_VISION_RETRIESOllama 瞬时故障（429/5xx/网络抖动）重试次数
configLOCAL_VISION_RETRY_BASE重试退避基数（秒，第 n 次等待 基数×2^(n-1)）
configLOCAL_VISION_MAX_DIMENSION可选大图缩放：（默认关闭）可让超长边大图在发给 Ollama 前自动等比缩小，防止 detailed 模式卡死；
configLOCAL_VISION_ZS_TRANSLATE中文描述会自动本地翻译成英文再检测（常见物体走词典直译，其余走本地 Ollama 翻译；=0 可关闭）。
configLOCAL_VISION_CONF_FLOOR可选。设为 0.15 等开启"结果为空时自动降置信度重试"（减少漏检，但可能增加低置信度假目标，数人场景请谨慎）；默认关闭保持稳定
configVISION_OUTPUT_DIR设置后强制所有生成文件写入该目录
configPADDLEOCR_KEEP_ONEDNN设为 1 保留 PaddleOCR 的 oneDNN（需 paddle 版本无 bug 或 GPU 版，见部署手册）
configPADDLE_PDX_CACHE_HOME
configDETECTION_MODELdetect_objects 默认 yolov8n.pt（首次自动下载约 6MB，可 换 yolov8s.pt 等）
configSEGMENTATION_MODEL默认分割模型
configDETECTION_TEXT_MODEL默认零样本检测模型
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

12/12 tools missing one or more hints — analyze_image (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); compare_images (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); image_info (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +9 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 2 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/yuhang-uestc/deepvision-local-mcp)](https://m8ven.ai/mcp/yuhang-uestc/deepvision-local-mcp)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: c9698cf19fc0baf4ba484eb65d119f9b12e9a80a
code hash: 1f54ff91a41da1d9b8a5dc25457ec5eea76f57ee7ea395c5cf006b0ccc7a4e9c
verified: 9/6/2026, 7:34:44 AM
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client