Publora

com.publora由 publora.com 發布官方發布者v1.1.1更新於 Oct 24, 2026

Schedule and publish to 10 social platforms: LinkedIn, X, Instagram, TikTok, YouTube, and more.

已驗證Streamable HTTP可網頁執行溝通與協作商業與電商

概覽

AI 產生的概覽

Publora 託管 MCP 伺服器讓助理在十個社群平台上草擬、排程與發佈內容，並查看互動數據。

可以做什麼
  • 列出、建立、檢視、修改與刪除貼文，支援排程或立即發佈
  • 為貼文附加圖片或影片，並管理媒體上傳與參照
  • 檢視帳戶方案、發佈配額與已連結的社群帳號
  • 讀取已發佈貼文的互動計數與帳號追蹤者數據
  • 在 LinkedIn 上按讚、留言、轉貼並查詢可 @ 提及的人
適用情境
適合在 AI 對話中管理社群媒體內容行事曆：向多個平台排程或發佈貼文、查看待發內容，以及了解近期貼文的表現。
執行需求
遠端端點 mcp.publora.com/mcp，無需安裝。需要 Publora 帳號並已連結社群帳號。認證方式為支援 OAuth 的用戶端以瀏覽器登入，或使用 Publora API 金鑰，透過 Authorization Bearer 或 x-publora-key 標頭傳送。也可用 Node.js 從儲存庫在本機執行 stdio 版本，需設定 PUBLORA_API_KEY。
安裝前請注意
此伺服器可發佈、編輯與刪除貼文和媒體，也能在 LinkedIn 發表或刪除按讚與留言，操作會直接影響公開帳號。需要 Publora API 金鑰或 OAuth 授權，金鑰應視為機密。統計工具僅支援 Mastodon 與 Bluesky，且需 Pro 或舊版 Premium 方案；本機儲存庫快照的工具集較舊且較少。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Publora，將其新增到工作區。
  2. 連接 所需的 憑證。它們會被私密儲存，絕不會在公開頁面上展示。
  3. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/com.publora%2Fmcp-server/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。 客戶端會在首次連接時完成 OAuth 登入。

{
  "mcpServers": {
    "publora": {
      "type": "http",
      "url": "https://mcp.publora.com/mcp"
    }
  }
}

README

Publora MCP Server

[smithery badge]

Official Model Context Protocol (MCP) server for Publora — control your social media scheduling directly from AI assistants like Claude, Cursor, and any MCP-compatible client.

No coding required. Just describe what you want in plain English:

"Schedule a LinkedIn post for tomorrow at 9am" "How did my last post perform?" "Post this to Twitter and LinkedIn"

Quick Start

Remote Server (Recommended)

Publora hosts an MCP server at mcp.publora.com/mcp — no installation needed.

Using Claude? Install it from the connectors directory: claude.ai/directory/publora. Select Connect, sign in to Publora, approve. No API key, no config file — on web, desktop and mobile alike.

Every other client:

1. Get your API key at app.publora.com/dashboard/api (API in the dashboard sidebar)

2. Add to your MCP client:

json
{  "mcpServers": {    "publora": {      "type": "http",      "url": "https://mcp.publora.com/mcp",      "headers": {        "Authorization": "Bearer sk_YOUR_API_KEY"      }    }  }}

Clients that support OAuth (Claude Code, Cursor, VS Code, Codex and others) can leave out headers and sign in through the browser instead.

3. Restart your client and start talking to your AI about social media!

Client Setup

Claude Code (CLI)
bash
claude mcp add --transport http --scope user publora https://mcp.publora.com/mcp

Run /mcp, select publora, choose Authenticate and sign in to Publora in the browser. No API key needed.

For CI or headless machines, send a static key instead:

bash
claude mcp add --transport http --scope user publora https://mcp.publora.com/mcp \  --header "Authorization: Bearer sk_YOUR_API_KEY"

The same entry can go in ~/.claude.json or a project .mcp.json (JSON above). Verify with the /mcp command.

Claude Desktop

Claude Desktop uses the same connectors as Claude on the web: open claude.ai/directory/publora and select Connect. There is no config file to edit.

Settings → Developer → Edit Config is only needed to run this repository locally over stdio, after cloning it and running npm install (see Local Development for how its tools differ from the hosted server):

json
{  "mcpServers": {    "publora": {      "command": "node",      "args": ["/path/to/mcp-server/src/stdio.js"],      "env": {        "PUBLORA_API_KEY": "sk_YOUR_API_KEY"      }    }  }}
Cursor

Create .cursor/mcp.json in your project:

json
{  "mcpServers": {    "publora": {      "type": "http",      "url": "https://mcp.publora.com/mcp",      "headers": {        "Authorization": "Bearer sk_YOUR_API_KEY"      }    }  }}
Local Development

Run your own instance:

bash
git clone https://github.com/publora/mcp-server.gitcd mcp-servernpm installPUBLORA_API_URL=https://api.publora.com npm start

Server runs on http://localhost:3100

The code in this repository is an April 2026 snapshot of the server. Its tool set is older: it has LinkedIn analytics and workspace tools, and lacks attach_media, complete_media, delete_media, prune_media_reference, account_context, post_stats, profile_stats, linkedin_create_reshare, linkedin_list_mentionables and the company_* Agency tools. Use the hosted server for the current tools.

Available Tools (20)

The hosted server at mcp.publora.com/mcp exposes:

Posts

ToolDescription
list_postsList posts with filters (status, platform, dates)
create_postCreate a draft, schedule a post, or publish now with publishNow: true; accepts mediaUrls and platformSettings
get_postGet post details and status
update_postEdit a draft or scheduled post: content, platforms, schedule, status, or publish it now with publishNow: true
delete_postDelete a post

Media

ToolDescription
attach_mediaAttach an image or video from ChatGPT to an existing post; leaves the post in draft
get_upload_urlGet a presigned URL for media upload
complete_mediaFinalize a file uploaded via get_upload_url
delete_mediaRemove a media slot from a post
prune_media_referenceRemove a stale media reference that delete_media cannot handle

Account and connections

ToolDescription
account_contextYour plan, available features, publishing quotas and schedule horizon — check before a batch of posts or after a quota error
list_connectionsList connected social accounts

Statistics (Mastodon and Bluesky, Pro plan or legacy Premium)

ToolDescription
post_statsEngagement counters for published posts
profile_statsFollowers, following and post count of a connected account

LinkedIn Engagement

ToolDescription
linkedin_create_reactionReact to a post
linkedin_delete_reactionRemove a reaction
linkedin_create_commentPost a comment on a LinkedIn post
linkedin_delete_commentDelete a comment
linkedin_create_reshareRepost/reshare a LinkedIn post
linkedin_list_mentionablesList people you can @mention in a LinkedIn post

LinkedIn analytics and workspace management are available through the REST API, not MCP. Full parameters: MCP Tools Reference.

Example Conversations

Schedule a post:

You: Schedule "Excited about our product launch!" to LinkedIn for tomorrow 9am AI: Done! Post scheduled for tomorrow at 9am EST.

Cross-platform posting:

You: Post "We're hiring!" to all my accounts AI: Published to Twitter, LinkedIn, and Bluesky.

Check engagement (Mastodon, Bluesky):

You: How did my last Bluesky post do? AI: 42 likes, 7 reposts and 3 replies so far.

Content calendar:

You: What do I have scheduled for next week? AI: 5 posts: Mon LinkedIn, Tue Twitter+LinkedIn, Wed LinkedIn...

Who Is This For?

  • Marketers — manage campaigns and check analytics via AI chat
  • Content creators — schedule posts without switching apps
  • Business owners — delegate social media tasks to AI
  • Developers — integrate Publora into AI-powered workflows

Supported Platforms

Twitter/X · LinkedIn · Instagram · Threads · TikTok · YouTube · Facebook · Bluesky · Mastodon · Telegram

Authentication

Clients that support OAuth 2.1 (Claude, Claude Code, Cursor, VS Code, Codex and others) sign in through the browser — no key to copy.

Everywhere else, use your Publora API key via:

  • Authorization: Bearer sk_... (recommended)
  • x-publora-key: sk_...

Get your key: app.publora.com/dashboard/api

Verification

bash
# Health checkcurl https://mcp.publora.com/health
# Test MCP handshakecurl -X POST https://mcp.publora.com/mcp \  -H "Content-Type: application/json" \  -H "Accept: application/json, text/event-stream" \  -H "Authorization: Bearer sk_YOUR_API_KEY" \  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0.0"}}}'

Documentation

Development

bash
# Installnpm install
# Run locallyPUBLORA_API_URL=https://api.publora.com npm start
# Run testsnpm test

Environment Variables

VariableDefaultDescription
PORT3100Server port
PUBLORA_API_URLhttps://api.publora.comBackend API URL

Related

License

MIT

Publora — Affordable social media API: free Starter plan with API and MCP access; Pro from $5.99 per account per month ($3.99 billed yearly)

來源：README.md，提交 a44e32c

工具

0
該伺服器需要登入，因此 SourceWeft 無法在沒有帳號的情況下讀取其工具，也未收錄。已連接帳號所能看到的內容可能因帳號及其權限而異。

版本歷史

1
  1. v1.1.1最新Sep 16, 2026

評分

已滿足適用檢查項的 85%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list，或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分