Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Descripción del creador (original en inglés)
AI-native commercial disruption intelligence for MCP clients and x402-powered agents.
Estos tres nunca se combinan en una sola puntuación: las opiniones, las mediciones y la popularidad son cosas distintas.
Todavía no escribimos un resumen sencillo para este. Abajo están los datos que leímos del registro.
Elige la app de IA que usas y copia la configuración.
Necesitas
¿Qué app usas?
Elige tu app arriba. La recordamos, así que la próxima vez el botón dirá “Instalar en …”.
Abre Claude Desktop → Settings → Developer → Edit Config y pega esto en claude_desktop_config.json
{
"mcpServers": {
"disruption-intelligence": {
"command": "npx",
"args": [
"-y",
"@forgemeshlabs/disruption-intelligence-mcp"
]
}
}
}Ejecuta esto en tu terminal
claude mcp add disruption-intelligence -- npx -y @forgemeshlabs/disruption-intelligence-mcpPégalo en .cursor/mcp.json de tu proyecto, o en ~/.cursor/mcp.json
{
"mcpServers": {
"disruption-intelligence": {
"command": "npx",
"args": [
"-y",
"@forgemeshlabs/disruption-intelligence-mcp"
]
}
}
}Tu navegador te pide permiso para abrir la app; luego la app muestra la configuración y te pide confirmar. Los valores de las claves quedan vacíos para que los completes tú.
Pégalo en .vscode/mcp.json de tu proyecto
{
"servers": {
"disruption-intelligence": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@forgemeshlabs/disruption-intelligence-mcp"
]
}
}
}Tu navegador te pide permiso para abrir la app; luego la app muestra la configuración y te pide confirmar. Los valores de las claves quedan vacíos para que los completes tú.
Este se ejecuta en tu computadora, y ChatGPT solo puede conectarse a servidores en internet. Elige otra app.
Tu elección se guarda en una cookie en este dispositivo; no necesitas cuenta.
Esta configuración se genera a partir de la ficha del creador en el registro. Si el README dice otra cosa, sigue el README.
Se ejecuta en tu computadora; la lista de herramientas aparece en tu app de IA después de instalarlo.
Revisamos información que cualquiera puede ver; no hemos leído el código. Las revisiones que no aplican no se cuentan. · Revisado el 7 nov 2026
El nombre en el registro se verificó con la cuenta de GitHub forgemeshlabs, dueña del repo
Todavía no hemos leído este repo en GitHub
Todavía no hemos leído este repo en GitHub
Este se ejecuta en tu computadora; no hay endpoint en internet
Se ejecuta en tu computadora y usa ajustes locales en su lugar
Se ejecuta en tu computadora; solo podemos leer listas de herramientas de endpoints en internet
Comparado con todos los servidores activos de esta categoría en el registro. Las estrellas solo cuentan cuando quien lo publica es dueño del repo.
Superó 1 de 1 revisiones básicas aplicables. No hemos leído el código. Antes de agregar una clave o un token, revisa qué acceso pide el servidor y usa una clave que tenga solo los permisos que necesitas.
El registro no indica ninguna clave obligatoria, aunque algunos servidores te piden iniciar sesión la primera vez que los usas.
Se ejecuta en tu computadora. Tu app de IA lo inicia cuando hace falta, y los datos no pasan por los servidores del creador (a menos que el propio servidor llame a un servicio en línea).
El repo de GitHub cambió por última vez –, y la última versión (0.1.11) llegó al registro hace 5 días.
Las apps compatibles con MCP, como Claude Desktop, Claude Code, Cursor y VS Code. También necesitas Node.js en tu computadora.
En la misma categoría: Spec Driven Development, Remote Desktop Commander, Zendesk
Servidores de la misma categoría hechos por otros creadores, ordenados por estrellas.
Cómo leer una tarjeta:★ Estrellas de GitHubiTres pilares: reseñas · revisiones · usoiActualizado = fecha en que se publicó la última versión en el registroi
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.
Zendesk MCP Pack — tickets, users, organizations via OAuth.
Copiado tal cual del repo del creador. PopNx MCP no lo ha revisado ni lo respalda. Se quitaron HTML, imágenes y scripts. Los enlaces llevan fuera de este sitio.
AI-native commercial disruption intelligence for MCP clients and x402-powered agents.
Disruption Intelligence MCP gives AI agents access to commercial disruption signals through an MCP server backed by the hosted Forgemesh API. It supports WARN/layoff intelligence, company context, geospatial territory disruption, location-only Ripple Index cards, Ripple Signals, Ripple Paths, Disruption Intelligence Ripple Reports, x402 payment challenge inspection, and economic signal workflows without exposing private scoring logic, ingestion systems, schemas, or infrastructure.
This package is a thin client around the hosted API:
https://disruption.forgemesh.io
Architecture:
Agent/MCP client -> this MCP server -> hosted Disruption Intelligence API
The MCP package does not contain engine internals, scoring logic, ingestion architecture, database schema, private topology, wallet addresses, or secrets.
npm install -g @forgemeshlabs/disruption-intelligence-mcp
Published package:
https://www.npmjs.com/package/@forgemeshlabs/disruption-intelligence-mcp
Source repo:
https://github.com/forgemeshlabs/disruption-intelligence-mcp
Local development:
npm install
npm run build node dist/index.js
Example config:
{
"mcpServers": { "disruption-intelligence": { "command": "npx", "args": ["@forgemeshlabs/disruption-intelligence-mcp"] } } }
See examples/claude-desktop-config.json.
| Tool | Endpoint | Cost behavior |
|---|---|---|
get_api_status | GET /health | Free |
get_discovery_metadata | GET /index.json, /llms.txt, /openapi.json, /.well-known/x402.json | Free |
inspect_x402_challenge | Unpaid request to a paid endpoint | Returns x402 challenge metadata |
analyze_territory_disruption | GET /territory/:zip/disruption?radius= | Paid; challenge-first by default |
search_company_context | GET /companies/search?q= | Paid; challenge-first by default |
get_company_risk_summary | GET /companies/:id/intelligence | Paid; challenge-first by default |
get_event_severity | GET /events/:id/severity | Paid; challenge-first by default; paid output includes confidence-rated industry_classification |
get_event_company_intel | GET /events/:id/company-intel | Paid; challenge-first by default; paid output includes confidence-rated industry_classification |
get_event_timeline | GET /events/:id/timeline | Paid; challenge-first by default |
search_gold_inventory | GET /ripple/search?q= | Compatibility tool name; free Ripple inventory counts and unlock pricing only |
get_ripple_index | GET /ripple/index?q=&scope=&limit= | Paid at $0.01; challenge-first by default; returns location-only Ripple index cards |
get_gold_signals | GET /ripple/signals?q=&limit=&state= | Compatibility tool name; paid at $0.10; challenge-first by default; returns Ripple Signals after settlement |
get_gold_brief | GET /ripple/brief?q=&scope=&limit= | Compatibility tool name; paid at $0.25; challenge-first by default; returns a Disruption Intelligence Ripple Report after settlement |
get_gold_sector_impacts | GET /ripple/signals/:id/sector-impacts | Compatibility tool name; paid at $0.15; challenge-first by default; returns Ripple Paths after settlement |
Free Ripple search is intentionally inventory-only. It returns counts, freshness, and unlock pricing without exposing commercial angles, evidence categories, source mix, signal IDs, company names, or raw source records.
get_ripple_index unlocks a low-cost location-only index for choosing where to dig next. It can return signal IDs, event IDs, regions, states, signal types, freshness/depth/confidence/score bands, and unlock URLs, while withholding company names, employee counts, commercial angles, sector names, spend areas, source records, and impact paths.
Paid Ripple endpoints expose distilled commercial intelligence. get_gold_signals returns Ripple Signal summaries, confidence bands, compact evidence labels, and Ripple Path inventory with an unlock endpoint. get_gold_sector_impacts unlocks the deeper operational map for one signal, including downstream spend categories such as fuel, food service, uniforms, maintenance, IT, logistics, office supplies, telecom, insurance, legal, cleaning, travel, and related vendor categories.
Paid event-level API responses now include industry_classification when event context is available. The hosted API returns the industry label, NAICS fields when present, derivation method, confidence level, source text when relevant, and a coverage note. The MCP remains a thin client: it does not infer industries locally and does not rewrite hosted WARN data.
Default mode is safe and non-settling. Free endpoints return API data directly. Paid endpoints are requested without payment credentials, so the hosted API can return an x402 402 Payment Required challenge.
When payment is required, this MCP returns structured payment instructions and challenge metadata instead of dumping an upstream error. It does not require a private key and does not settle payments.
Future paid execution should be opt-in and delegated to a trusted wallet or payment client.
No environment variables are read. The API base URL is fixed to https://disruption.forgemesh.io; every request is bounded (60 s timeout, 2 MB response cap, no redirects) and inspect_x402_challenge only accepts a plain path on that host.
No wallet private key is required or accepted by this package. Paid endpoint calls return x402 challenge metadata for an external wallet or payment client to settle.
API docs and product context:
https://github.com/forgemeshlabs/disruption-intelligence
Hosted API:
https://disruption.forgemesh.io
This repository is an agent-facing thin client wrapper around the hosted API. It intentionally excludes engine code, scoring formulas, ingestion internals, database details, operational topology, wallet addresses, private keys, and secrets.