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 HaoyueQin/picture-identification-MCP --skill picidentgit clone --depth 1 https://github.com/HaoyueQin/picture-identification-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/haoyueqin/picture-identification-mcp/picident)<a href="https://agentmods.dev/skills/haoyueqin/picture-identification-mcp/picident"><img src="https://agentmods.dev/badge/skills/haoyueqin/picture-identification-mcp/picident/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/haoyueqin/picture-identification-mcp/picident"><img src="https://agentmods.dev/badge/skills/haoyueqin/picture-identification-mcp/picident.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 | $0.00100 | $0.01304 |
| Opus 5 | $0.00050 | $0.00652 |
| Sonnet 5 | $0.00020 | $0.00261 |
| Haiku 4.5 | $0.00010 | $0.00130 |
Grade A, and why
picident scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
bash <(curl -fsSL https://raw.githubusercontent.com/HaoyueQin/picture-identification-MCP/main-v2/bin/picident-launcher.sh) --stdio How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
picident-mcp — 识图 MCP server
picident-mcp 是纯 MCP server:把图片(本地路径 / http(s) URL / data: URI)转发给 有视觉能力的模型 API,返回文字描述给主模型推理。支持 4 种协议、多供应商自动降级、 图片自动压缩到 2048px 长边、凭据只走环境变量。
安装(智能体可执行步骤)
方式 A:下载预编译二进制(推荐)
-
确定平台:Windows / Linux (x64|arm64) / macOS (x64|arm64)。
-
执行本仓库的启动器(自动从 GitHub Releases 下载对应平台二进制并缓存到
~/.cache/picident(macOS/Linux)或%LOCALAPPDATA%\picident\bin(Windows)):-
macOS / Linux(bash):
bash <(curl -fsSL https://raw.githubusercontent.com/HaoyueQin/picture-identification-MCP/main-v2/bin/picident-launcher.sh) --stdio -
Windows(PowerShell,先下载到本地再执行):
Invoke-WebRequest -Uri "https://raw.githubusercontent.com/HaoyueQin/picture-identification-MCP/main-v2/bin/picident-launcher.ps1" -OutFile "$env:TEMP\picident-launcher.ps1" powershell -ExecutionPolicy Bypass -File "$env:TEMP\picident-launcher.ps1" --stdio
或直接把 launcher 脚本下载到本地后执行。launcher 也支持设置
PICIDENT_BIN环境变量指向已有二进制以跳过下载。 -
-
验证:
picident-server --help输出帮助即安装成功。安全说明:launcher 下载的二进制会先校验 GitHub Releases 发布的
.sha256校验和(校验失败会拒绝运行);脚本本体来自本仓库,执行前 可自行查看内容确认。
方式 B:从源码构建
git clone https://github.com/HaoyueQin/picture-identification-MCP
cd picture-identification-MCP
cargo build --release -p picident-server
# → target/release/picident-server(.exe)
配置 config.toml
- 将仓库中的
config.example.toml复制到系统配置目录并改名为config.toml:- Windows:
%APPDATA%\picident\config.toml - Linux:
~/.config/picident/config.toml - macOS:
~/Library/Application Support/picident/config.toml
- Windows:
- 启用至少一个 provider(
open_ai_compat最通用,base_url 示例https://api.openai.com/v1,也可用 DeepSeek / OpenRouter / 硅基流动等任何 OpenAI 兼容网关;本地 Ollama 无需密钥)。
注册到 MCP 客户端
在智能体的 mcpServers 配置中加入(stdio 模式,推荐):
{
"mcpServers": {
"picident": {
"command": "<picident-server 二进制绝对路径>",
"args": ["--stdio"],
"env": {
"PICIDENT__providers__openai__token": "<你的 API key>"
}
}
}
}
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.
- 11d ago First seen · 105 lines · 100 tokens per session scan A ef9a74c245f4
picident is a skill published in the GitHub repository HaoyueQin/picture-identification-MCP (6 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 1,304 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
blockrun
Pay-per-call access to AI models, real-time data, media generation and multi-chain RPC over x402 micropayments (USDC on Base or Solana). No API keys, no accounts, no subscriptions. Start here when you have the BlockRun MCP installed and need to know WHICH tool answers a question, how the wallet works, or how to make a…
setup
Configure the Qdrant Power after installation. Use this skill for missing uvx, missing environment variables, unapproved environment variables, unavailable Qdrant tools, "Failed to connect" errors, and setup requests.
segment-anything-model
Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.
flowllm-dev
FlowLLM repository development guidance. Use when working in the flowllm codebase to implement, debug, test, review, or document FlowLLM runtime behavior, including CLI/client calls, services, application wiring, jobs, steps, components, configuration, streaming, registry registration, and tests.
ai-economics
Compute AI cost, energy and agent-verification numbers instead of estimating them. Use whenever the user asks what AI work costs (tokens, context windows, agent-hours, model routing), how much energy or CO2 an LLM workload uses, which model is cheaper per verified task, how many agents a review team can support, what…
describe-image
Describe images (charts, diagrams, tables, screenshots) using Vision AI. Use as fallback when you cannot read an image file directly. Supports batch processing of folders.