Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add SoLongAdios/zhipu-vision-mcp --skill image-analyzegit clone --depth 1 https://github.com/SoLongAdios/zhipu-vision-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/solongadios/zhipu-vision-mcp/image-analyze)<a href="https://agentmods.dev/skills/solongadios/zhipu-vision-mcp/image-analyze"><img src="https://agentmods.dev/badge/skills/solongadios/zhipu-vision-mcp/image-analyze/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/solongadios/zhipu-vision-mcp/image-analyze"><img src="https://agentmods.dev/badge/skills/solongadios/zhipu-vision-mcp/image-analyze.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00121 | $0.00864 |
| Opus 5 | $0.00060 | $0.00432 |
| Sonnet 5 | $0.00024 | $0.00173 |
| Haiku 4.5 | $0.00012 | $0.00086 |
Grade A, and why
image-analyze scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
图片识别(image-analyze)
当用户要求识别/理解/分析图片——例如"识别这张图片""图片里有什么""看图回答""描述图片内容""提取/识别图片中的文字(OCR)"——时,调用视觉 MCP 工具 analyze_image(由 zhipu-vision MCP server 提供)。该工具内置多模型自动故障转移:按优先级依次尝试 glm-4.6v-flash → glm-4.1v-thinking-flash → glm-4v-flash → mimo:mimo-v2.5 → mimo:mimo-v2-omni,限流/失败自动切换下一个,无需手动干预。前三个为智谱免费模型,mimo 为收费兜底(智谱限流时自动切换);如需使用其他收费模型(kimi/qwen/gemini/gpt 等),用 model 参数显式指定(见下)。
调用方式
工具参数:
image(必填):图片输入,三种形式任选其一:- 本地文件绝对路径(如
C:/Users/xx/a.png) - http(s) 图片 URL
- base64 data URI(
data:image/...;base64,...)
- 本地文件绝对路径(如
question(可选):对图片的提问;用户未指定时默认"请描述这张图片"。可以代用户补充更有针对性的问题(如"识别图中的文字""图中有几个物体""图片是什么场景"),以提升回答质量。model(可选):手动指定模型,格式provider:model(如glm-4.1v-thinking-flash、mimo:mimo-v2.5、kimi:kimi-k3、qwen:qwen-vl-max、gemini:gemini-2.5-flash、openai:gpt-4o);指定后不自动切换。仅在用户明确要求用某个模型时使用。
注意事项
- 支持格式:png / jpg / jpeg / gif / webp / bmp / svg / ico;其他格式需先转换为支持的格式。
- 用户给出的是相对路径或文件名时,先解析为绝对路径再传入。
- 返回的
structuredContent.model是实际使用的provider/model,可据此向用户说明用的哪个模型(如发生切换)。 - 若返回
isError: true,说明所有候选模型都失败,把错误信息转述给用户并给出处理建议:- 429(该模型当前访问量过大):免费模型限流,已自动尝试收费兜底(默认 mimo);若仍失败,可建议用户用
model参数指定其他收费模型(如kimi:kimi-k3/qwen:qwen-vl-max),或稍后重试; - 401:对应 provider 的 API key 无效,请检查
ZHIPU_API_KEY/MIMO_API_KEY; - 404(模型不存在):
VISION_MODEL_CHAIN中模型名拼写有误。
- 429(该模型当前访问量过大):免费模型限流,已自动尝试收费兜底(默认 mimo);若仍失败,可建议用户用
- 一次调用分析一张图片;多张图片可多次调用
analyze_image。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 31 lines · 121 tokens per session scan A 79891c1e0134
image-analyze is a skill published in the GitHub repository SoLongAdios/zhipu-vision-mcp (0 stars, last pushed 28d ago), licensed MIT. It adds 121 tokens to every session and 864 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.