Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add adelaidasofia/luma-mcp/plugin install luma-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/mcp/adelaidasofia/luma-mcp/luma)<a href="https://agentmods.dev/mcp/adelaidasofia/luma-mcp/luma"><img src="https://agentmods.dev/badge/mcp/adelaidasofia/luma-mcp/luma/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/adelaidasofia/luma-mcp/luma"><img src="https://agentmods.dev/badge/mcp/adelaidasofia/luma-mcp/luma.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
luma 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 9d 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
{
"luma": {
"type": "stdio",
"command": "fastmcp",
"args": [
"run",
"${CLAUDE_PLUGIN_ROOT}/luma_mcp/server.py"
]
}
}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.
- 9d ago First seen · 10 lines scan A 1c7168968a68
luma is an MCP server published in the GitHub repository adelaidasofia/luma-mcp (0 stars, last pushed 2d 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 2026-08-31.
Other mcp servers, from other repositories
korean-rnd-regs-mcp
A local MCP server for reviewing South Korean national research-and-development regulations. MCP is a way for an AI agent to call an external tool.
apollo-mcp
MCP server "apollo-mcp" as configured in adelaidasofia/apollo-mcp. Launched with https://github.com/adelaidasofia/apollo-mcp/releases/download/v0.1.0/apollo-mcp.. Needs 1 environment variable to run.
google-workspace-mcp
MCP server "google-workspace-mcp" as configured in adelaidasofia/google-workspace-mcp. Launched with https://github.com/adelaidasofia/google-workspace-mcp/releases/download/v0.1.0/g. Needs 2 environment variables to run.
socialloop-mcp
SocialLoop: AI-native event platform — sell tickets, manage guests, run affiliates & promo codes. Remote server at mcp.socialloop.ai.
mcp-nevent
Talk to your live-events CRM (campaigns, analytics, paid ads, segments) in Claude and ChatGPT. Runs locally from the mcp-nevent npm package. Needs 2 environment variables to run.
slack-mcp
MCP server "slack-mcp" as configured in adelaidasofia/slack-mcp. Launched with https://github.com/adelaidasofia/slack-mcp/releases/download/v0.1.1/slack-mcp.mc. Needs 1 environment variable to run.