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 agentmods add instructions/img-src-io/mcp/claude-mdgit clone --depth 1 https://github.com/img-src-io/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/instructions/img-src-io/mcp/claude-md)<a href="https://agentmods.dev/instructions/img-src-io/mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/img-src-io/mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.00727 | $0.00727 |
| Opus 5 | $0.00364 | $0.00364 |
| Sonnet 5 | $0.00145 | $0.00145 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
mcp CLAUDE.md 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 3d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Is
This is the @img-src/mcp-server — an MCP (Model Context Protocol) server that enables AI assistants to interact with the img-src.io image processing API programmatically.
Commands
pnpm install # Install dependencies
pnpm build # Build TypeScript to dist/
pnpm start # Start MCP server (stdio transport)
pnpm test # Run tests with Vitest
pnpm type-check # TypeScript type checking
pnpm lint # ESLint
CI Checks (what PR builds run)
pnpm build && pnpm lint && pnpm type-check && pnpm test
CI matrix: Node.js 20, 22 on ubuntu-latest.
Architecture
Single-file Structure
src/
├── index.ts # Main MCP server implementation
└── index.test.ts # Tests
Key Dependencies
@modelcontextprotocol/sdk— MCP SDK for server implementationzod— Runtime schema validation
Available Tools
| Tool | Description |
|---|---|
upload_image |
Upload image from local file or URL |
list_images |
List images in folder with pagination |
search_images |
Search by filename/path |
get_image |
Get image metadata by ID |
delete_image |
Delete an image |
get_usage |
View usage statistics |
get_settings |
Get account settings |
get_cdn_url |
Generate CDN URL with transformations |
Configuration
The server requires IMG_SRC_API_KEY environment variable:
{
"mcpServers": {
"img-src": {
"command": "npx",
"args": ["@img-src/mcp-server"],
"env": {
"IMG_SRC_API_KEY": "imgsrc_your_api_key"
}
}
}
}
Testing
Uses Vitest for testing. Tests mock the MCP SDK and HTTP requests.
pnpm test # Run all tests
pnpm test -- --watch # Watch mode
CD/Publishing
The server is published to npm automatically when a git tag is pushed.
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.
- 3d ago First seen · 114 lines · 727 tokens per session scan A d67b99dd02ff
mcp CLAUDE.md is an instructions file published in the GitHub repository img-src-io/mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 727 tokens to every session, about $0.0036 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 instructions, from other repositories
cloudinary_npm AGENTS.md
Instructions for cloudinary/cloudinary_npm, covering contributor guide for coding agents, commands, testing, project structure and code style.
gitpic AGENTS.md
AGENTS.md instructions for tarnish233/gitpic, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
20i-MCP CLAUDE.md
Instructions for Cbrown35/20i-MCP, covering claude.md, project overview, development commands, build & development and testing & analysis.
wraps CLAUDE.md
Claude Code instructions for wraps-team/wraps, covering claude.md - wraps project context, workflow, error handling, project overview and architecture overview.
cloudinary_npm CLAUDE.md
Instructions for cloudinary/cloudinary_npm, a project described as: Upload, transform, optimize, and manage images and videos with Cloudinary from Node.js.
wraps AGENTS.md
AGENTS.md instructions for wraps-team/wraps, covering agents.md - wraps, prerequisites, install, deploy infrastructure (no install needed) and or install globally.