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 YC-CLT/VLM-mcp --skill using-vlm-mcpgit clone --depth 1 https://github.com/YC-CLT/VLM-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/yc-clt/vlm-mcp/using-vlm-mcp)<a href="https://agentmods.dev/skills/yc-clt/vlm-mcp/using-vlm-mcp"><img src="https://agentmods.dev/badge/skills/yc-clt/vlm-mcp/using-vlm-mcp/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/yc-clt/vlm-mcp/using-vlm-mcp"><img src="https://agentmods.dev/badge/skills/yc-clt/vlm-mcp/using-vlm-mcp.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 | $0.00021 | $0.01104 |
| Opus 5 | $0.00010 | $0.00552 |
| Sonnet 5 | $0.00004 | $0.00221 |
| Haiku 4.5 | $0.00002 | $0.00110 |
Grade A, and why
using-vlm-mcp 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using VLM-MCP
Overview
通过 VLM-mcp MCP 工具对图片进行单次分析、模板处理或多轮对话。核心原则：无会话必传图，有会话可追问，用完必须关。
触发场景
用户提供图片并要求：描述、分析、OCR 提取文字、图表解读、翻译图中文字、基于图片问答。
OCR 优先用 ocr_image。不要优先用 analyze_image + template: "ocr" ，效果不好再换。
不用此 skill 的场景： 纯文本分析（无图片）、非 VLM-mcp 工具的图片处理。
快速参考
调用方式：run_mcp(server_name="vlm-mcp", tool_name="工具名", args={...})。
image 支持三种格式：本地绝对路径（如 D:/images/photo.png）、URL（https://...）、base64 data URI。
| 工具 | 操作 | args |
|---|---|---|
ocr_image |
本地 OCR | image → [{text, box, confidence}, ...] |
analyze_image |
自由描述 | image, prompt |
analyze_image |
模板描述 | image, template: "describe" |
analyze_image |
模板 OCR | image, template: "ocr" |
analyze_image |
图表解读 | image, template: "chart" |
analyze_image |
翻译图中文字 | image, template: "translate", params: {target_lang} |
analyze_image |
图片问答 | image, template: "qa", params: {question} |
analyze_image |
指定后端 | image, prompt, backend |
create_session |
创建会话 | backend（可选）→ {session_id} |
close_session |
关闭会话 | session_id |
list_sessions |
活跃会话 | 无 |
list_backends_tool |
可用后端 | 无 |
list_templates |
可用模板 | 无 |
analyze_image 返回：{text, model, tokens_used, cache_hit, session_id}。
使用模式
模板分析
先用 list_templates 查看可用模板，再按上方快速参考表调用（独立调用，无需 session）。
多轮对话
s = run_mcp("vlm-mcp", "create_session", args={"backend": "dashscope"}) # 可选 backend
sid = s["session_id"]
run_mcp("vlm-mcp", "analyze_image", args={"image": "doc.png", "prompt": "总结", "session_id": sid})
run_mcp("vlm-mcp", "analyze_image", args={"prompt": "第三节？", "session_id": sid}) # 追问可不传图
run_mcp("vlm-mcp", "close_session", args={"session_id": sid}) # 用完必须关
常见错误
| 错误 | 现象 | 正确做法 |
|---|---|---|
无会话忘传 image |
INVALID_PARAMS: image is required |
无会话时 image 必传 |
| 不关会话 | 占槽位（每后端最多 5 个），后续创建报 SESSION_FULL |
用完 close_session；若已占满，list_sessions 查孤儿 → 逐一 close_session |
同时传 template 和 prompt |
template 优先，prompt 被忽略 |
只传其中一个 |
| 会话内换后端 | SESSION_BACKEND_MISMATCH |
新建 session 换后端 |
image 用相对路径 |
IMAGE_NOT_FOUND |
用绝对路径、URL 或 base64 |
用 analyze_image + template: "ocr" 做简单提取 |
浪费在线 API 额度、延迟高 | 优先用 ocr_image |
| 模板名拼错 | TEMPLATE_NOT_FOUND |
list_templates 查看可用模板名 |
| 忘传模板必填参数 | INVALID_PARAMS: Missing required param |
list_templates 查看模板所需参数 |
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.
- 7d ago Changed · -30 lines · -14 tokens per session e5a0a8fb1fe4
- 11d ago First seen · 104 lines · 35 tokens per session scan A 62fc97b833db
using-vlm-mcp is a skill published in the GitHub repository YC-CLT/VLM-mcp (0 stars, last pushed 8d ago), licensed MIT. It adds 21 tokens to every session and 1,104 once invoked, about $0.0001 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
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.