Postoria MCP Server

Postoria MCP Server

Enables MCP-compatible clients to create, schedule, queue, inspect, and delete Postoria posts through the Postoria Public API.

Category
访问服务器

README

Postoria MCP Server

Postoria MCP Server connects MCP-compatible AI clients to Postoria.

Use it to list workspaces, find social accounts and queues, upload or import media, publish posts, schedule posts, add posts to queues, check post status, and delete posts.

Package

npx -y @postoria/mcp-server

Features

  • Local stdio transport for desktop and IDE MCP clients
  • Streamable HTTP transport for hosted MCP clients
  • Works with Postoria Public API keys
  • Supports Postoria workspaces, social accounts, queues, media, and posts
  • MCP Registry metadata in server.json

Supported tools

Tool Description
list_workspaces List available Postoria workspaces
list_social_accounts List social accounts in a workspace
list_queues List queues in a workspace
create_media_upload Create a signed media upload URL
complete_media_upload Complete a media upload after raw bytes are uploaded
upload_media_from_file Upload a local file from stdio clients
import_media_from_url Import media from a public URL
get_media Get media status and details
publish_post_now Publish a post immediately
schedule_post Schedule a post for a specific time
add_post_to_queue Add a post to a Postoria queue
get_post Get post status and details
delete_post Delete a post created through the Public API

upload_media_from_file is available only in local stdio mode. It is not exposed through the hosted Streamable HTTP endpoint.

Requirements

  • Node.js 20+
  • A Postoria Public API key

Local stdio usage

Add this to your MCP client configuration:

{
  "mcpServers": {
    "postoria": {
      "command": "npx",
      "args": ["-y", "@postoria/mcp-server"],
      "env": {
        "POSTORIA_API_KEY": "ptr_your_api_key_here"
      }
    }
  }
}

Hosted Streamable HTTP usage

Hosted endpoint:

https://mcp.postoria.io/mcp

Send your Postoria API key as a Bearer token:

Authorization: Bearer ptr_your_api_key_here

Media upload options

Use import_media_from_url when the media is already available through a public URL.

Use create_media_upload when the client will upload raw file bytes to the returned signed upload URL. After the raw bytes are uploaded with PUT, call complete_media_upload.

Use upload_media_from_file in local stdio mode when the media file exists on the same machine where the MCP server is running.

Run from source

npm install
npm run build

Run in local stdio mode:

POSTORIA_API_KEY=ptr_your_api_key_here npm run dev:stdio

Run in local HTTP mode:

npm run dev:http

HTTP mode requires the MCP client to send the Postoria API key in the Authorization header. POSTORIA_API_KEY is used by local stdio mode only.

Local HTTP endpoint:

http://localhost:3000/mcp

Health check:

http://localhost:3000/health

MCP Registry

server.json includes distribution metadata for:

  • remote Streamable HTTP endpoint: https://mcp.postoria.io/mcp
  • local npm stdio package: @postoria/mcp-server

Security notes

  • The MCP server does not store Postoria API keys.
  • Local stdio mode reads POSTORIA_API_KEY from the environment.
  • Hosted HTTP mode requires Authorization: Bearer <api_key> on MCP initialization.
  • POSTORIA_API_KEY is used by local stdio mode only.
  • delete_post is destructive and should only be called after user confirmation.

Development

npm install
npm run typecheck
npm run build
npm run format:check

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选