Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Verifica RFCs contra las listas del SAT (69, 69-B EFOS, 69-B Bis, CSD): veredicto de riesgo fiscal.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://sat69.watr.mx/connectRun this in your terminal
claude mcp add --transport http sat69 https://sat69.watr.mx/connectPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"sat69": {
"url": "https://sat69.watr.mx/connect"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"sat69": {
"type": "http",
"url": "https://sat69.watr.mx/connect"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
https://sat69.watr.mx/connectMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
We have not read this server’s tool list yet; we check endpoints in rotation.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account edbror, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Not checked yet; we check endpoints in rotation
Not checked yet; we check endpoints in rotation
Not checked yet; we read the tool list when we check the endpoint
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.1.0) reached the registry 26 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Spec Driven Development, Remote Desktop Commander, MCP Server Autocad Lisp Helper
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
High-precision static analysis and debug server for AutoCAD AutoLISP (.lsp) files.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Servidor MCP (Model Context Protocol) en Python / FastMCP para consultar las listas públicas del SAT:
Misma arquitectura que el MCP de movilizaciones de la SSC-CDMX: FastMCP con transporte stdio + Streamable HTTP, OAuth 2.1 (WorkOS AuthKit) con fallback a bearer estático, persistencia en Turso (libSQL), proxy de descarga opcional, y despliegue en Render con cron externo (GitHub Actions). Sin OCR: los CSV del SAT ya vienen estructurados.
| Tool | Qué hace |
|---|---|
verificar_rfc | Verifica un RFC → veredicto de riesgo (CRITICO…LIMPIO, o NO_VERIFICADO si alguna lista está sin datos). |
verificar_lote | Valida hasta 500 RFCs; devuelve sólo hallazgos por severidad. |
buscar_nombre | Búsqueda por nombre/razón social (FTS5, insensible a acentos). |
estado_datos | Vigencia declarada por el SAT, conteos y última importación. |
actualizar_datos | Descarga + sincroniza los listados (idempotente por hash, con guard de frescura). |
resumen_cartera | Brief ejecutivo en lenguaje natural de una cartera (hasta 500 RFCs). |
Prioridad de severidad entre listas: 69-B > 69-B Bis > 69.
⚠️ `resumen_cartera` es el único tool con IA, y sólo redacta. El riesgo de cada RFC lo calcula el motor de reglas (determinista); el modelo recibe esos veredictos ya resueltos y escribe el brief — nunca decide un riesgo ni cambia uno. Proveedor conmutable con LLM_PROVIDER (qwen por default vía DashScope; también anthropic y gemini). Sin IA configurada el tool igual responde: devuelve los datos deterministas con resumen: null.
Riesgo: CRITICO (EFOS definitivo) · ALTO (EFOS presunto) · MEDIO (69 firme/exigible/no localizado) · BAJO (desvirtuado/sentencia favorable) · INFORMATIVO (69 cancelado/condonado) · LIMPIO.
Los resultados reflejan la última importación de los archivos públicos del SAT. No constituyen asesoría fiscal ni legal.
CSV del SAT (Latin-1) ┌────────── FastMCP ──────────┐
│ fetcher (httpx + proxy opcional) │ verificar_rfc / _lote │ ▼ │ buscar_nombre / estado_datos │ pipeline (parse 69 / 69b) ──► SQLite ──┤ actualizar_datos │ │ (FTS5 unicode61, triggers) ▲ │ └──────────┬──────────────────┘ ▼ │ │ stdio (server.py) + HTTP (web.py) Turso (libSQL, durable) ◄── push │ └► pull al arranque │ └─────────────────── /health /refresh /reload
/health (abierto), /refresh y /reload (bearer M2M), /mcp (OAuth o bearer).cd sat69-mcp
python -m venv .venv && source .venv/bin/activate pip install -e ".[dev]"
python -c "from sat69 import database as db, config; db.init_db(config.settings.db_path)" python -c "from sat69.pipeline import process_import; print(process_import())"
pytest -q
{
"mcpServers": { "sat69": { "command": "sat69-mcp" } } }
(o "command": "python", "args": ["-m", "sat69"] con el venv activo.)
render.yaml provisiona el servicio web con runtime Python nativo (sin Docker):
render.yaml.sync:false): MCP_API_KEY (bearer), opcional AUTHKIT_DOMAIN+BASE_URL (OAuth), TURSO_DATABASE_URL+TURSO_AUTH_TOKEN.POST https:// .onrender.com/mcp.MCP_API_KEY): simple, protege /mcp, /refresh, /reload.AUTHKIT_DOMAIN + BASE_URL y /mcp pasa a OAuth con Dynamic Client Registration; el bearer sigue protegiendo los endpoints M2M..github/workflows/refresh.yml hace POST /refresh diario (11:30 UTC ≈ 05:30 CDMX). Secrets del repo: RENDER_BASE_URL, MCP_API_KEY. Manual: workflow_dispatch (con force).
SQLite local (efímero en Render, /tmp) atiende las consultas; Turso es el almacén durable que sobrevive redeploys. Al arrancar se hace pull de Turso; tras cada actualizar_datos//refresh se hace push. Sin TURSO_*, corre en modo local puro.
FETCH_PROXY o DATAIMPULSE_* enrutan sólo la descarga de los CSV. En pruebas el SAT no bloqueó IPs de datacenter (descargas 200 directas), así que normalmente no hace falta; se conserva por paridad y resiliencia.
Listado_Completo_69-B.csv (~14 k registros, 20 columnas, header en línea 3).Firmes.csv, Cancelados.csv, NoLocalizados.csv, Exigibles.csv, Sentencias.csv, Condonados.csv (~½ millón de registros, 6 columnas). URLs en config.py.