convez.ai
MCP ServerEscrita & ConteúdoAvançado
n2ns

n2n-post2site

n2ns/n2n-post2site

Bridge MCP para publicação de conteúdo com segurança e intenção

Ver no GitHub
BomPluginScore · de 0 a 100

MCP server que funciona como ponte entre assistentes de IA e APIs de publicação de conteúdo. Permite rascunhar, editar e publicar posts em blogs e CMSs através de um contrato API mínimo, sem acesso a banco de dados, shell ou infraestrutura — ideal para content publishing assistido.

Instalação

$npx convez-ai n2ns/n2n-post2site

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
8
Forks
2
Acompanhando
1
Saúde
75%
Último commit
há 1 semana
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Rascunar e publicar posts de blog com assistência de IA
  • Criar artigos técnicos, guias de produto e release notes
  • Gerar conteúdo localizado (multi-idioma) de forma controlada
  • Manter workflow editorial seguro com draft-by-default

Veredito

Ferramenta robusta para times que precisam publicar conteúdo via IA com segurança e auditoria. Modelo de draft obrigatório e API mínima reduzem riscos; exige backend customizado que implemente o Content Publishing API Contract.

README

A tradução para o português deste README ainda está na fila.

n2n-post2site

AI-assisted content publishing MCP server for blogs, guides, and other categorized content.

npm version npm total downloads license MCP Protocol node version


Draft with AI. Publish with intent.

n2n-post2site is an open-source Model Context Protocol (MCP) server that lets an AI assistant draft, edit, review, and publish website content through a narrow Content Publishing API Contract. It is a local MCP bridge between your IDE assistant and your website content API — intentionally small, with no database access, shell access, deployment access, payment access, or user administration access.

💡 What is n2n-post2site?

n2n-post2site gives AI coding assistants a structured path to draft and publish website content without exposing the database, file system, or deployment layer. Your backend implements the Content Publishing API Contract; the MCP server forwards AI tool calls to it.

Use it for blog posts, product guides, technical notes, release notes, and localized article drafts. It is not a CMS — no admin panel, no storage backend, no image uploads (v1), no deployment workflow.

📰 Publishing model

n2n-post2site classifies content with an optional content_scope:

Contentcontent_scopeExample
Unscopedomitted or emptytechnical notes, announcements, changelogs
Scopedkind:keyproduct:evisa-helper

The backend defines which content_scope kinds are valid and which content types require one. Scoped content should only be written after the assistant reads controlled context with n2n_get_scope_context.

The assistant should follow this workflow:

  1. Call n2n_get_capabilities.
  2. Search existing content with n2n_list_posts.
  3. For scoped content, call n2n_get_scope_context.
  4. Create or update one locale at a time.
  5. Resume unfinished work with n2n_list_drafts, n2n_get_post, and n2n_update_draft.
  6. Review the draft.
  7. Publish only through n2n_publish_post.

🚀 Quick start

Requirements: Node.js 22+, an MCP-capable client, a site-scoped API key, and a backend that implements the Content Publishing API Contract.

1. Configure your MCP client

Using the npm package:

{
  "mcpServers": {
    "n2n-post2site": {
      "command": "npx",
      "args": ["-y", "n2n-post2site"],
      "env": {
        "CONTENT_API_BASE_URL": "https://your-site.com/api/v1/mcp",
        "CONTENT_API_KEY": "your-api-key"
      }
    }
  }
}

Using a local checkout:

{
  "mcpServers": {
    "n2n-post2site": {
      "command": "node",
      "args": ["/path/to/n2n-post2site/dist/index.js"],
      "env": {
        "CONTENT_API_BASE_URL": "https://your-site.com/api/v1/mcp",
        "CONTENT_API_KEY": "your-api-key"
      }
    }
  }
}
  • CONTENT_API_BASE_URL: base URL of your protected content API. Keep path and field mapping in the backend adapter.
  • CONTENT_API_KEY: site-scoped API key. Do not put it in prompts, article content, or screenshots.

Bind one server instance to exactly one website.

🔗 Backend API contract

n2n-post2site connects to any backend that implements the Content Publishing API Contract. The contract defines the required endpoints, payload rules, and security requirements.

See Backend API Contract for the full specification.

🛠️ MCP tools

  • Discovery: read backend capabilities, list existing posts, and load scope context before drafting.
  • Drafting: create posts, update posts one locale at a time, and resume unpublished drafts.
  • Publishing: publish an approved draft through an explicit publish step.

See Tools reference for parameter schemas and call examples.

📝 Content format

  • Submit one locale per create or update call.
  • Use Markdown for content.
  • Use fenced code blocks for commands, JSON, YAML, and code examples.
  • Use Markdown image syntax for images.
  • Always include descriptive image alt text.
  • Reference public image URLs or existing site paths.
  • This MCP does not upload images in v1.

Image example:

![Product dashboard showing content status](/images/guides/content-status.png)

🔐 Security and governance notes

n2n-post2site should not expose:

  • Delete operations.
  • Product configuration writes.
  • Pricing plan writes.
  • User administration.
  • Payment or subscription administration.
  • Database queries.
  • Log access.
  • Shell commands.
  • Deployment or server operations.

Recommended backend behavior:

  • Sanitize backend errors before returning them to the AI client.
  • Use a site-scoped API key with the minimum permissions needed.
  • Create drafts by default.
  • Keep create/update and publish separate.
  • Set published_at on the backend, not from MCP input.

📖 Related docs

  • Backend API Contract: Endpoints, payload rules, and security requirements for backend implementors.
  • Architecture: Runtime layers, module boundaries, and request flow in the MCP server.
  • Tools reference: MCP tool parameter schemas and call examples.
  • Roadmap: Planned features and what's coming next.
  • Changelog: Version history and release notes.
  • Contributing: How to report issues and contribute.
  • Security: How to report vulnerabilities.

📄 License

This project is licensed under the MIT License.


Built by N2NS Lab, the open-source lab of datafrog.io for practical AI developer tools.

Ver o original no GitHub

Bom para

Relacionados