Borrowing it
Nothing to install: this file belongs to hoangsonww/AI-RAG-Assistant-Chatbot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hoangsonww/AI-RAG-Assistant-Chatbot/master/.agents/skills/lumina-mcp-server/SKILL.mdgit clone --depth 1 https://github.com/hoangsonww/AI-RAG-Assistant-ChatbotWrote 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/hoangsonww/ai-rag-assistant-chatbot/lumina-mcp-server)<a href="https://agentmods.dev/skills/hoangsonww/ai-rag-assistant-chatbot/lumina-mcp-server"><img src="https://agentmods.dev/badge/skills/hoangsonww/ai-rag-assistant-chatbot/lumina-mcp-server/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/hoangsonww/ai-rag-assistant-chatbot/lumina-mcp-server"><img src="https://agentmods.dev/badge/skills/hoangsonww/ai-rag-assistant-chatbot/lumina-mcp-server.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 | $0.00048 | $0.00368 |
| Opus 5 | $0.00024 | $0.00184 |
| Sonnet 5 | $0.00010 | $0.00074 |
| Haiku 4.5 | $0.00005 | $0.00037 |
Grade A, and why
lumina-mcp-server 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 12d 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
Lumina MCP Server
Overview
Use this skill for the standalone MCP server at mcp_server/. The server implements the Model Context Protocol with 32 tools across 8 categories, 7 resources, and 6 prompts.
Load The Right Reference
- Read
references/file-map.mdto locate the tool, resource, prompt, or middleware that owns a behavior. - Read
references/tool-development.mdwhen adding or modifying MCP tools.
Preserve The MCP Contract
- Tool names and
input_schemadefinitions are external contracts — MCP clients depend on them. - Keep each tool category in its own module under
tools/. - Extend by subclassing
ToolHandler(ABC)withname,description,input_schema, andhandle(). - Register new tools in the category module's
register(cfg)function. - New categories require a new module and a
_ToolRegistryentry intools/__init__.py.
Keep Middleware Composable
- Authentication, rate limiting, and validation flow through
MiddlewareChain. - Do not bypass middleware for individual tools.
- Configuration overrides via environment variables (
MCP_API_KEY,MCP_RATE_LIMIT,MCP_LOG_LEVEL).
Validate Carefully
- Run
python -m compileall mcp_serverfor compile-time validation. - Use
python -m mcp_server --log-level DEBUGfor startup smoke testing when dependencies are installed. - Do not assume external services (Pinecone, Git repos) are available during validation.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 36 lines · 48 tokens per session scan A 793ce0ee96ee
lumina-mcp-server is a skill published in the GitHub repository hoangsonww/AI-RAG-Assistant-Chatbot (47 stars, last pushed 4d ago), licensed MIT. It adds 48 tokens to every session and 368 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
darto-add-route
Add or modify HTTP endpoints in a Darto (Dart) web app — verbs, path/query params, request-body reading, route groups, and Context response helpers. Use when building or changing API routes in a project that depends on the darto package (import 'package:darto/darto.dart'). Not for Express/Node — Darto handlers take a…
darto-validate-request
Validate the body, query, params, or headers of a Darto (Dart) request using the zValidator middleware and zard (Zod-style) schemas. Use when adding input validation to a Darto endpoint, defining a z.map/z.string/z.int schema, reading validated data with c.req.valid, or customizing the validation error response.…
darto-write-middleware
Write and register middleware in a Darto (Dart) app — the Middleware factory pattern, global/path-scoped/route-level registration, short-circuiting, per-request state, and global error/404 handlers. Use when adding cross-cutting behavior (auth, logging, CORS, timing) or configuring app.onError / app.notFound in a…
darto-scaffold-project
Scaffold, run, and build a Darto (Dart) web project using the dartocli — create a new project with a NestJS-style module structure, run a hot-reload dev server, compile a production binary, and generate a typed API client. Use when starting a new Darto app, setting up the project layout, or configuring dev/build…
codigo-automacao
Skills para desenvolvimento de software, debug, APIs, automações no-code e uso avançado de ferramentas de IA para desenvolvimento. Use quando precisar de diagnóstico de bugs, construção de APIs, containerização, testes automatizados, integrações ou engenharia de prompts.
express
Build Express.js routers and middleware with request validation, async error handling, and clear application structure.