Server data from the Official MCP Registry
Schedule and publish social posts to 11 platforms with media, campaigns, analytics and AI captions
About
Schedule and publish social posts to 11 platforms with media, campaigns, analytics and AI captions
Remote endpoints: streamable-http: https://mcp.posteverywhere.ai/mcp
Security Report
This is a well-structured MCP server for PostEverywhere's social media API with proper authentication via API keys and reasonable permission scopes matching its purpose. The code demonstrates good security practices including input validation via Zod schemas, secure credential handling (API key required via env var), and clear separation of concerns. Minor code quality observations exist but do not constitute security vulnerabilities. Supply chain analysis found 3 known vulnerabilities in dependencies (0 critical, 3 high severity). Package verification found 1 issue.
3 files analyzed Β· 8 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
Permissions Required
This plugin requests these system permissions. Most are normal for its category.
What You'll Need
Set these up before or after installing:
Environment variable: POSTEVERYWHERE_API_KEY
How to Install & Connect
Available as Local & Remote
This plugin can run on your machine or connect to a hosted endpoint. during install.
Documentation
View on GitHubFrom the project's GitHub README.
@posteverywhere/mcp β Social Media MCP Server for Claude, ChatGPT, Cursor, Codex & AI Agents
mcp-name: io.github.posteverywhere/mcp
Official Model Context Protocol server for PostEverywhere β let Claude Code, Claude Desktop, ChatGPT (via the hosted connector), Cursor, OpenAI Codex, and other MCP-compatible AI clients schedule and publish social media posts to Instagram, TikTok, YouTube, LinkedIn, Facebook, X (Twitter), Threads, and Pinterest using natural language.
π‘ Building a programmatic integration? Use the companion
@posteverywhere/sdkNode.js SDK instead β full TypeScript types, retry handling, error classes.
π Quick Links
| Resource | URL |
|---|---|
| π Homepage | posteverywhere.ai |
| π οΈ Developers landing page | posteverywhere.ai/developers |
| π API Documentation | developers.posteverywhere.ai |
| π¦ This MCP on npm | npmjs.com/package/@posteverywhere/mcp |
| π» This MCP on GitHub | github.com/posteverywhere/mcp |
| π¦ Node SDK (npm) | npmjs.com/package/@posteverywhere/sdk |
| π» Node SDK (GitHub) | github.com/posteverywhere/sdk |
| β¨οΈ CLI & Agent Skill (npm) | npmjs.com/package/@posteverywhere/cli |
| β¨οΈ CLI & Agent Skill (GitHub) | github.com/posteverywhere/cli |
| ποΈ Dashboard | app.posteverywhere.ai |
| π Get an API key | app.posteverywhere.ai/developers |
| π΅ Pricing | posteverywhere.ai/pricing |
| π Help Center | posteverywhere.ai/support |
| π§ Model Context Protocol | modelcontextprotocol.io |
| π Issues / bug reports | github.com/posteverywhere/mcp/issues |
| π§ Support | support@posteverywhere.ai |
What is MCP?
Model Context Protocol (MCP) is an open standard from Anthropic that lets AI assistants connect to external tools and data sources. Once you connect this MCP server, your AI assistant can:
- Schedule posts across all your connected social accounts
- Generate AI images and attach them to posts
- List, edit, retry, and delete scheduled or published posts
- Surface per-platform publishing results including failure reasons
β¦all from natural-language prompts inside Claude, Cursor, or any MCP-compatible client.
Quick Start
1. Get an API key
Sign up free at posteverywhere.ai/signup (7-day trial), connect your social accounts, then create an API key at Settings β Developers. Choose your scopes:
- Read β list accounts, posts, and media
- Write β create, edit, delete posts and media
- AI β generate images using AI models
2. Add the MCP server to your AI client
Claude Code
claude mcp add posteverywhere -- npx -y @posteverywhere/mcp
Then set POSTEVERYWHERE_API_KEY in your environment, or pass it as an argument:
claude mcp add posteverywhere -e POSTEVERYWHERE_API_KEY=pe_live_your_key_here -- npx -y @posteverywhere/mcp
Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"posteverywhere": {
"command": "npx",
"args": ["-y", "@posteverywhere/mcp"],
"env": {
"POSTEVERYWHERE_API_KEY": "pe_live_your_key_here"
}
}
}
}
Restart Claude Desktop. The PostEverywhere tools will appear in the π¨ menu.
π Claude Desktop MCP docs β
Cursor
In Cursor, open Settings β MCP β Add new MCP server and paste:
{
"posteverywhere": {
"command": "npx",
"args": ["-y", "@posteverywhere/mcp"],
"env": {
"POSTEVERYWHERE_API_KEY": "pe_live_your_key_here"
}
}
}
π Cursor MCP docs β
Other MCP clients
This package exposes a standard stdio MCP server. Any MCP-compatible client can connect using the same configuration shape.
3. Try it out
Once connected, ask your AI assistant things like:
"List my connected social accounts"
"Schedule a post to all my accounts for tomorrow at 2pm: Just shipped a new feature π"
"Show me my recent posts and their publishing status"
"Generate an image of a sunset over mountains in 16:9 and post it to Instagram and X"
"Retry the failed destinations on my latest post"
"What are my last 10 posts on TikTok?"
Available Tools
Accounts
list_accountsβ list all connected social accounts and their health statusget_accountβ get details for a specific account (token expiry, can-post status)
Posts
list_postsβ list posts filtered by status (scheduled,published,failed,draft) or platform. Drafts include their target accounts + per-platform content so you can review them before publishing.get_postβ get full details for a single post including all destinations (for drafts, the saved accounts + per-platform content)create_postβ publish now, schedule for later, or save as a draft for human review (draft: true)schedule_postβ publish or schedule a draft (the approval step β passscheduled_for, orpublish_now: true)update_postβ modify a scheduled or draft post (content, schedule time, accounts)delete_postβ delete a scheduled or draft postget_post_resultsβ per-platform publishing results, errors, and live URLsretry_failed_postβ retry every failed destination of a post
π§βπΌ Human-in-the-loop drafts β let the agent draft posts for you to approve before anything goes live:
- "Draft a LinkedIn post about our launch β don't publish it yet" β
create_post(draft: true)- "Show me my drafts" β
list_posts(status: "draft")/get_post- "Looks good β schedule it for Tuesday 9am" β
schedule_post(scheduled_for: β¦)(or "publish it now" βpublish_now: true)Drafts are saved in your PostEverywhere account and never publish until you schedule them β review them in the app or via the agent.
Media
list_mediaβ list files in your media libraryget_mediaβ get media file details and processing statusupload_media_from_urlβ import an image from any public URL into the library (one call, returns amedia_idready forcreate_post)delete_mediaβ remove a media file
AI
generate_imageβ generate an image from a text prompt (4 models, 7 aspect ratios)
π Full tool reference and parameters β
Example Prompts
These all work out of the box once the server is connected:
Scheduling
- "Schedule a Christmas post for December 25th at 9am: Merry Christmas to our amazing community π"
- "Post this to Instagram and TikTok only: Behind-the-scenes of our latest feature drop"
- "Queue up a week of daily morning posts starting Monday at 9am"
Content generation
- "Generate a 9:16 image of a coffee shop at sunrise and schedule it as a TikTok post for tomorrow"
- "Create a square image of abstract green shapes for a LinkedIn carousel"
Monitoring
- "What posts failed in the last week and why?"
- "Show me the publishing results for my last Instagram Reel"
- "Which of my accounts need to be reconnected?"
Recovery
- "Retry the failed LinkedIn destination on post abc-123"
- "Delete all my draft posts older than 30 days"
Each natural-language prompt maps to one or more MCP tool calls β the agent figures out the right sequence.
Supported Platforms
All eight platforms work on every plan:
- Instagram β feed, reels, stories, carousels
- TikTok β videos, photo carousels
- YouTube β videos with thumbnails, descriptions, tags
- LinkedIn β text, images, video, document carousels
- Facebook β pages, video, reels, multi-image
- X (Twitter) β text, threads, media (tier-aware char limits)
- Threads β text and media posts
- Pinterest β pins to boards
Configuration
| Environment variable | Required | Description |
|---|---|---|
POSTEVERYWHERE_API_KEY | β | Your API key from Settings β Developers. Format: pe_live_... |
POSTEVERYWHERE_BASE_URL | β | Override base URL (default https://app.posteverywhere.ai). Useful for self-hosted deployments. |
Rate Limits
| Resource | Per minute | Per hour | Per day |
|---|---|---|---|
| General API calls | 60 | 1,000 | β |
| Posts | 60 | 200 | 1,000 |
| AI generation | β | 60 | β |
Hitting a 429? The MCP server returns a clear rate_limit_exceeded code with retry_after seconds β the agent will know to wait and retry.
How it compares
| This MCP server | PostEverywhere SDK | Direct REST API | |
|---|---|---|---|
| Use with Claude / Cursor / MCP clients | β Native | β | β |
| Use in Node.js code | β (use SDK) | β | β |
| Natural-language scheduling | β | β | β |
| TypeScript types | β | β | Manual |
| Auto-retry / backoff | β | β | Manual |
| Best for | AI-assisted social media | Programmatic integrations | Any HTTP client / language |
Documentation
- π Full API Reference β every tool, every parameter
- π Authentication & Scopes
- β οΈ Error Handling β including the
retryableflag agents should respect - β±οΈ Rate Limits β per-minute, per-hour, per-day caps
- πΌοΈ Media Requirements β file size, format, aspect ratio per platform
- π€ Agent System Prompts β recommended prompts for AI agent integrations
- π§ About MCP β the open protocol behind this server
- π Quick Start Guide β first post in 60 seconds
- π Webhooks β receive publish events on your endpoints
- π·οΈ API Scopes β fine-grained permission control
- π Changelog β what's new in the API
MCP & AI Tooling Resources
- π§ Model Context Protocol β Specification
- π οΈ MCP Quickstart for Users
- π¨βπ» MCP Quickstart for Developers
- ποΈ Browse all MCP servers (community list)
- πΌ Anthropic β MCP announcement
- π§ Claude Code β Get started
- π§ Claude Code β MCP setup
- π₯οΈ Claude Desktop
- π±οΈ Cursor β MCP docs
- π¬ Anthropic Claude
PostEverywhere Around the Web
- π PostEverywhere Homepage
- π οΈ Developers Landing Page β overview of API, SDK, MCP, integrations
- π€ AI Agents Page β using PostEverywhere with Claude, ChatGPT, Cursor, and more
- π΅ Pricing β Starter ($19), Growth ($39), Pro ($79); 7-day free trial
- βοΈ Blog β guides, tutorials, product updates
- π Help Center β guides, troubleshooting, FAQs
- ποΈ Dashboard (sign in)
- β¨ Sign Up β 7-day free trial
- π Get an API key
- π¦ Node.js SDK (npm)
- π» Node.js SDK (GitHub)
- π¦ MCP Server (npm β this package)
- π» MCP Server (GitHub β this repo)
- π’ PostEverywhere on GitHub
Per-Platform Schedulers
PostEverywhere is the backend for all of these β every plan includes every platform:
- π· Instagram Scheduler β feed posts, reels, stories, carousels
- π΅ TikTok Scheduler β videos, photo carousels, full content disclosure flags
- πΊ YouTube Scheduler β videos with thumbnails, tags, descriptions, privacy controls
- πΌ LinkedIn Scheduler β personal + Company Page posts, document carousels, video
- π Facebook Scheduler β Pages, Reels, video, multi-image carousels
- π¦ X (Twitter), Threads, Pinterest β all included on every plan
Related
- π¦
@posteverywhere/sdkβ Node.js / TypeScript SDK (npm) - π posteverywhere.ai β Web dashboard, AI Studio, calendar UI
- π Help Center β Guides, troubleshooting, FAQ
- π΅ Pricing β From $19/mo, 7-day free trial
Support
- π§ Email: support@posteverywhere.ai
- π Issues: github.com/posteverywhere/mcp/issues
- π¬ Help Center
License
MIT β see LICENSE.
Built by the team at PostEverywhere. The smarter way to schedule social media to Instagram, TikTok, YouTube, LinkedIn, Facebook, X, Threads, and Pinterest β now with native MCP support for AI agents.
Reviews
No reviews yet
Be the first to review this server!
More Developer Tools MCP Servers
Git
Freeby Modelcontextprotocol Β· Developer Tools
Read, search, and manipulate Git repositories programmatically
Fetch
Freeby Modelcontextprotocol Β· Developer Tools
Web content fetching and conversion for efficient LLM usage
Toleno
Freeby Toleno Β· Developer Tools
Toleno Network MCP Server β Manage your Toleno mining account with Claude AI using natural language.
mcp-creator-python
Freeby mcp-marketplace Β· Developer Tools
Create, build, and publish Python MCP servers to PyPI β conversationally.
MCP Marketplace
Freeby mcp-marketplace Β· Developer Tools
Search and install MCP servers from inside your AI client.
MarkItDown
Freeby Microsoft Β· Content & Media
Convert files (PDF, Word, Excel, images, audio) to Markdown for LLM consumption
