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.
git clone --depth 1 https://github.com/luminarylane/fal-mcp-serverWrote 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/mcp/luminarylane/fal-mcp-server/fal-ai)<a href="https://agentmods.dev/mcp/luminarylane/fal-mcp-server/fal-ai"><img src="https://agentmods.dev/badge/mcp/luminarylane/fal-mcp-server/fal-ai/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/mcp/luminarylane/fal-mcp-server/fal-ai"><img src="https://agentmods.dev/badge/mcp/luminarylane/fal-mcp-server/fal-ai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
fal-ai 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
{
"fal-ai": {
"command": "uvx",
"args": [
"--from",
"fal-mcp-server==1.8.0",
"fal-mcp"
],
"env": {
"FAL_KEY": "${FAL_KEY}"
}
}
}What else .mcp.json configures
This page is one entry in a file that holds 6. Installing the file brings all of them; each is measured and scanned on its own page.
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 · 13 lines scan A e4ebeffb25f8
fal-ai is an MCP server published in the GitHub repository luminarylane/fal-mcp-server (52 stars, last pushed 4mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 2026-08-30.
Other mcp servers, from other repositories
openai-compatible-imagegen
MCP server "openai-compatible-imagegen" as configured in Syh1906/openai-compatible-imagegen. Runs dist/server.mjs with node.
scuffed-painter
MCP server "scuffed-painter" as configured in viktor-haag/scuffed-painter. Runs locally from the scuffed-painter Python package.
pixara-mcp
MCP server that lets LLMs generate and edit images through OpenRouter's Image API. Runs locally from the @pinkpixel/pixara-mcp npm package.
avots-mcp
Image, video, audio, face-swap, talking avatars and chat across 300+ AI models, one balance. Remote server at mcp.avots.ai.
claude-imagine
MCP server for generating images in Claude Code and Cursor — supports local image generation tools like ComfyUI and other backends. Runs locally from the claude-imagine npm package.
comfyui-mcp
MCP server for ComfyUI: text-to-image, variations, img2img refine, upscale, image proxy. Runs locally from the @miller-joe/comfyui-mcp npm package. Needs 3 environment variables to run.