Connect PostEverywhere to Claude, Codex, or any AI agent
Paste one URL. 33 tools, 12 webhook events, 11 platforms. Connect Claude Code, Cursor, Windsurf, or Codex CLI to the hosted MCP server and your agent is scheduling posts in under 60 seconds.
Used by 2,831+ happy customers
Connect your AI agent
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.
MCP server
https://mcp.posteverywhere.aiThe easiest way. No terminal, no API key to copy. Shown here in Claude Desktop.
- 1
Open Connectors and click Add
In Claude, go to Settings then Connectors and click the + to add a custom connector.
- 2
Paste the server URL
Name it PostEverywhere and paste https://mcp.posteverywhere.ai. No client ID or secret needed.
- 3
Click Connect
PostEverywhere shows up in your connector list. Hit Connect to start the sign-in.
- 4
Approve access
Review what the agent can do, then Approve. This creates a revocable key for you, nothing to copy or paste.
- 5
All 33 tools, ready
Claude can now schedule, retry, generate captions, read analytics, and manage webhooks across 11 platforms.
- 6
Ask your agent to post
Try "connect to PostEverywhere" or "schedule this to LinkedIn for 9am." It is live.
33 MCP tools, webhooks, campaigns, bulk operations, AI caption generation, and a hosted server you connect with one URL.
Read the launch notes →Local config block for every MCP client
Most people should use the hosted server above. If you would rather run the open-source server on your own machine, every client follows the Model Context Protocol spec, so the same JSON works across Claude Desktop, Cursor, Cline, and Windsurf. Zed nests it under context_servers, and Codex CLI uses TOML.
~/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" }
}
}
}~/.cursor/mcp.json
{
"mcpServers": {
"posteverywhere": {
"command": "npx",
"args": ["-y", "@posteverywhere/mcp"],
"env": { "POSTEVERYWHERE_API_KEY": "pe_live_YOUR_KEY" }
}
}
}~/.codex/config.toml
[mcp_servers.posteverywhere]
command = "npx"
args = ["-y", "@posteverywhere/mcp"]
env = { POSTEVERYWHERE_API_KEY = "pe_live_YOUR_KEY" }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_serversinstead ofmcpServers, 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, and 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.”
npx @posteverywhere/cliBuilt for agents: structured JSON output and a bundled SKILL.md for auto-discovery.
Why agent builders pick PostEverywhere
The execution layer is the boring half of an agent. It should also be the reliable half.
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.
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; for agency setups across client workspaces, see 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.
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, and account health are all on the same client. See the developers page 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)
Any framework that speaks HTTP
LangChain, CrewAI, AutoGen, LlamaIndex, Vercel AI SDK, 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 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, the SDK, and the MCP server.
PostEverywhere agents FAQ
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.