# AI Social Media Agent: Connect ChatGPT, Claude or Any Agent **Source:** https://posteverywhere.ai/agents --- MCP server v1.4.1 · 33 toolsREST API · 29 endpoints · 12 webhook events # Turn ChatGPT, Claude, or any AI agent into your social media manager Paste one URL. 33 tools, 12 webhook events, 11 platforms. Connect ChatGPT, Claude, Cursor, or Codex CLI to the hosted MCP server, and your AI agent is [scheduling posts](https://posteverywhere.ai/social-media-scheduler) in under 60 seconds. [Start 7 day free trial](https://app.posteverywhere.ai/signup)$0 charged today, cancel anytime Used by **2,831** happy customers Works withChatGPTClaude CodeClaude DesktopCursorCodex CLIWindsurfClineZed ## Connect your AI agent to social media Pick how you want to connect. The hosted server runs on our infrastructure, so there is nothing to install and nothing running on your machine. - **Open the MCP connection page.** Start a PostEverywhere plan and open this page to get your hosted MCP server URL. - **Add the hosted MCP server to your agent.** Paste the one URL into ChatGPT (Developer Mode), Claude Code, Cursor, Windsurf, or Codex CLI. The server runs on our infrastructure, so there is nothing to install. - **Connect your social accounts.** Authorize the platforms you want the agent to publish to, across all 11 supported networks. - **Prompt your agent to schedule a post.** Ask your agent to draft and schedule a post; it uses the 33 MCP tools to publish across your connected platforms. MCP server `https://mcp.posteverywhere.ai`CopyIn your browserIn your terminalRun locallyThe easiest way. No terminal, no API key to copy. Shown here in Claude Desktop. - 1Open Connectors and click AddIn Claude, go to Settings then Connectors and click the + to add a custom connector. - 2Paste the server URLName it PostEverywhere and paste https://mcp.posteverywhere.ai. No client ID or secret needed. - 3Click ConnectPostEverywhere shows up in your connector list. Hit Connect to start the sign-in. - 4Approve accessReview what the agent can do, then Approve. This creates a revocable key for you, nothing to copy or paste. - 5All 33 tools, readyClaude can now schedule, retry, generate captions, read analytics, and manage webhooks across 11 platforms. - 6Ask your agent to postTry "connect to PostEverywhere" or "schedule this to LinkedIn for 9am." It is live. ## The social media MCP server for AI agents PostEverywhere runs a hosted **social media MCP server** at `mcp.posteverywhere.ai`. Model Context Protocol (MCP) is the open standard that lets AI agents call external tools, so once the server is connected, an agent like ChatGPT, Claude, or Cursor can schedule social media posts, generate captions and images, retry failed posts, and read analytics across all 11 platforms in plain language. There is nothing to install and no glue code to write. The full tool list and per-client setup live on the [MCP server page](https://posteverywhere.ai/mcp), and [our vendor comparison](https://posteverywhere.ai/blog/social-media-mcp-servers) maps who else has one. Connect the [hosted server](#quick-start) with one URL, or run the open-source [@posteverywhere/mcp](https://www.npmjs.com/package/@posteverywhere/mcp) server on your own machine. Both expose the same 33 tools to any MCP-compatible client. To schedule social media posts from Claude, add the server, connect your accounts, and prompt the agent to publish. v1.4 just shipped33 MCP tools, webhooks, campaigns, bulk operations, AI caption generation, and a hosted server you connect with one URL. [Read the launch notes →](https://posteverywhere.ai/blog/api-v1-4-launch)Prefer to run it locally? ## Local config block for every MCP client Most people should use the [hosted server](#quick-start) above. If you would rather run the open-source server on your own machine, every client follows the [Model Context Protocol](https://modelcontextprotocol.io) spec, so the same JSON works across Claude Desktop, Cursor, Cline, and Windsurf. Zed nests it under `context_servers`, and Codex CLI uses TOML. Claude Desktoprequires full quit + relaunch`~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) `%APPDATA%\Claude\claude_desktop_config.json` (Windows) `{ "mcpServers": { "posteverywhere": { "command": "npx", "args": ["-y", "@posteverywhere/mcp"], "env": { "POSTEVERYWHERE_API_KEY": "pe_live_YOUR_KEY" } } } }`Cursorno restart needed`~/.cursor/mcp.json` `{ "mcpServers": { "posteverywhere": { "command": "npx", "args": ["-y", "@posteverywhere/mcp"], "env": { "POSTEVERYWHERE_API_KEY": "pe_live_YOUR_KEY" } } } }`Codex CLITOML, not JSON`~/.codex/config.toml` `[mcp_servers.posteverywhere] command = "npx" args = ["-y", "@posteverywhere/mcp"] env = { POSTEVERYWHERE_API_KEY = "pe_live_YOUR_KEY" }`Cline, Windsurf, and Zed - Cline Same JSON block, added via the MCP Servers panel in VS Code. - Windsurf Same JSON block, file `~/.codeium/windsurf/mcp_config.json`. - Zed Same shape, nested under `context_servers` instead of `mcpServers`, in `~/.config/zed/settings.json`. ## Prompts that work today Paste any of these into your agent once the server is connected. Each maps onto real MCP tools covering scheduling, [AI captions](https://posteverywhere.ai/ai-content-generator), and [analytics](https://posteverywhere.ai/social-media-analytics), no glue code required. “Schedule this draft to LinkedIn and X for Tuesday at 9am Pacific. Optimise the caption for each platform.” “Retry every TikTok post that failed in the last 7 days, but skip any video over 60 seconds.” “Pull my Instagram engagement metrics for May, then suggest three posting-time changes for June.” “Generate three caption variants for a product-launch carousel, then bulk-schedule them across the week.” “Subscribe to post.failed and account.disconnected events, route them to my Discord webhook.” Official packagesMIT license[@posteverywhere/mcp](https://www.npmjs.com/package/@posteverywhere/mcp)MCP server · v1.4.1 · 33 tools`npx -y @posteverywhere/mcp`[npm →](https://www.npmjs.com/package/@posteverywhere/mcp)[GitHub →](https://github.com/posteverywhere/mcp)[@posteverywhere/sdk](https://www.npmjs.com/package/@posteverywhere/sdk)Node.js SDK · v1.4.0`npm install @posteverywhere/sdk`[npm →](https://www.npmjs.com/package/@posteverywhere/sdk)[GitHub →](https://github.com/posteverywhere/sdk)[@posteverywhere/cli](https://www.npmjs.com/package/@posteverywhere/cli)CLI · v0.2.1`npx @posteverywhere/cli`Built for agents: structured JSON output and a bundled SKILL.md for auto-discovery. [npm →](https://www.npmjs.com/package/@posteverywhere/cli)[Docs →](https://developers.posteverywhere.ai) ## Built for builders Why agent builders pick PostEverywhere The [execution layer](https://posteverywhere.ai/social-media-automation) is the boring half of an agent. It should also be the reliable half. Your agent gets the same surface a human gets in the dashboard, through 33 MCP tools and 29 REST endpoints. 33 MCP tools, not five. The MCP server exposes the full surface: posts, campaigns, webhooks, bulk ops, media, account health, analytics, caption generation. Your agent can reason about all of it, not just create_post.Webhooks instead of polling. 12 event types, HMAC-signed. Your agent reacts when something happens instead of burning tokens checking every minute.Bulk ops to 50 per call. A 30-day calendar ships in roughly 3 requests. Bulk-retry-by-filter recovers an entire batch from a flaky platform in one call.Pre-flight account health. GET /v1/accounts/:id/health returns can_post, token expiry, and recent failures. Your agent checks before it posts, so a stale token never silently kills a publishing run. ## Real agent patterns What you can build Five agent patterns running on this API today. For a full walkthrough, read [how to build an AI social media agent](https://posteverywhere.ai/blog/build-an-ai-social-media-agent-with-posteverywhere); for agency setups across client workspaces, see [multi-account management](https://posteverywhere.ai/multi-account-management). Daily content agent. Watches your blog RSS, drafts platform-specific captions with Claude, generates an image via /v1/ai/generate-image, schedules across LinkedIn, X, and Threads.Self-healing retry agent. Subscribes to post.failed webhooks. Reads the error, decides whether to re-encode, retime, or skip, then calls bulk-retry. No human in the loop until something genuinely odd happens.Engagement-aware scheduler. Pulls /v1/analytics/summary weekly, ranks posting windows by engagement, rewrites next week's schedule.Multi-client agency bot. One agent per client, grouped via the campaigns API. /v1/me tells the agent which workspace it lives in, so the same code spins up for client 12 or client 412.Repurposing pipeline. Takes a YouTube upload, drafts a LinkedIn long-post, an X thread, three Instagram carousel slides, and a Bluesky teaser, then schedules each at the platform's best slot. Around 8 API calls end to end. ## Your first SDK call Building a long-running agent rather than working in an editor? The Node SDK wraps all 29 REST endpoints with typed resources. Schedule a postTypeScript`import PostEverywhere from '@posteverywhere/sdk'; const client = new PostEverywhere({ apiKey: process.env.POSTEVERYWHERE_API_KEY }); const post = await client.posts.create({ account_ids: [123], content: 'Shipping today.', scheduled_for: '2026-06-17T09:00:00Z', });`Webhooks, campaigns, [bulk operations](https://posteverywhere.ai/bulk-scheduling), and account health are all on the same client. See the [developers page](https://posteverywhere.ai/developers) for the full surface. ## Works with the agent stack you already run If your agent can issue a Bearer-authenticated POST, it can use PostEverywhere. ### Native MCP clients (zero glue code) ChatGPTClaude CodeClaude DesktopCursorClineWindsurfZed ### Any framework that speaks HTTP LangChain, CrewAI, AutoGen, LlamaIndex, Vercel AI SDK, [OpenClaw](https://posteverywhere.ai/openclaw), or your own loop with fetch and an LLM of your choice. Either way, your agent can [post to all social media at once](https://posteverywhere.ai/post-to-all-social-media-at-once) through one API. ## Included on every paid plan from $29/mo 7-day free trial, no separate developer tier, no enterprise call. The same key works for the [REST API](https://posteverywhere.ai/social-media-api), the SDK, and the MCP server. [Start free trial](https://app.posteverywhere.ai/signup)[View full pricing →](https://posteverywhere.ai/pricing) ## PostEverywhere agents FAQ ### Can I build an AI social media agent with PostEverywhere? Yes, that is exactly what the MCP server, REST API, and SDK exist for. Point any AI agent (Claude, Cursor, Codex, or your own LangChain or CrewAI loop) at the hosted server and it can draft, schedule, and publish across all 11 platforms, react to webhook events, and check account health before it posts. Most teams have a working AI social media agent connected in under a minute. ### Do I need an API key, or can I use OAuth? API keys today. They are the right primitive for a single-tenant agent talking to its own workspace. Keys start with pe_live_ and work across the REST API, SDK, and MCP server. ### How is this different from Zapier or n8n? Zapier and n8n are visual workflow builders, great for "when X, do Y" plumbing. PostEverywhere is the social-media execution layer your code-level agent calls directly. No webhook-to-Zap-to-API hop, no per-task pricing. Your agent reasons in your runtime and posts via one HTTP call. ### Does the MCP server work with Cursor, Cline, Windsurf, and Zed? Yes. Anything that speaks the MCP protocol works. The config block is identical for Claude Desktop, Cursor, Cline, and Windsurf; Zed nests it under context_servers; Codex CLI uses TOML. ### Why doesn't the tool show up after I add the config? Most common cause: npx is not on PATH in the client's environment, or a JSON syntax error in the config. Claude Desktop also needs a full quit and relaunch (not just closing the window). Check the MCP logs in your client if tools are missing. ### What if my agent posts the same thing twice? Subscribe to post.published webhooks and reconcile against your agent's own memory before scheduling more. The posts list endpoint also supports filtering by content search and date range, so the agent can check for near-duplicates first. ### What's the rate limit? 60 requests per minute on the API. Responses include X-RateLimit headers, and a 429 comes with Retry-After. For bulk publishing use POST /v1/posts/bulk (one request, up to 50 posts) instead of looping. ### Is there a social media MCP server? Yes. PostEverywhere runs a hosted social media MCP server at mcp.posteverywhere.ai with 33 tools; the /mcp page documents every tool and setup path. Model Context Protocol is the open standard that lets AI agents call external tools, so any MCP-compatible client (ChatGPT, Claude, Cursor, Codex, Cline, Windsurf, Zed) can schedule posts, generate media, and read analytics across all 11 platforms once the server is connected. There is nothing to install with the hosted server, or you can run the open-source @posteverywhere/mcp package locally. ### How do I schedule social media posts with MCP? Connect the PostEverywhere MCP server to your agent, authorize your social accounts, then prompt the agent in plain language, for example "schedule this post to LinkedIn and X for Tuesday at 9am." The agent uses the MCP tools to publish across any of the 11 connected platforms. The hosted server at mcp.posteverywhere.ai needs one URL and your API key, with nothing to install. ### Can I schedule social media posts from Claude? Yes. Add the PostEverywhere MCP server to Claude Code or Claude Desktop, connect your accounts, and ask Claude to draft and schedule posts. Claude calls the 33 MCP tools directly to publish across all 11 platforms, so you never leave the chat. Cursor, Codex CLI, Cline, Windsurf, and Zed work the same way. ### Does the MCP server work with ChatGPT? Yes. ChatGPT supports custom remote MCP servers through Developer Mode on Plus, Pro, Business, and Enterprise plans: turn on Developer Mode under Settings, then Connectors, add a custom connector with the URL https://mcp.posteverywhere.ai, and authorize with your PostEverywhere API key. ChatGPT can then schedule posts, generate media, and read analytics across all 11 platforms. You can also wire the REST API into a Custom GPT using Actions. Free ChatGPT accounts cannot add custom connectors yet.