# MCP Server · PostLake Docs

> Markdown version of https://docs.postlake.dev/mcp . The canonical page for humans.
> PostLake is the social media API for AI agents: https://postlake.dev/llms.txt

PostLake runs a hosted **MCP server**: the open standard that lets AI agents use external tools. Connect once and your agent can publish, schedule and pull analytics across every network, just by you asking in plain language.

## Server URL

```
https://api.postlake.dev/mcp
```

## Connect in three steps

 - **Open your agent's connector settings.** In Claude: Settings → Connectors → Add custom connector. ChatGPT, Cursor and others have an equivalent "add MCP server" option.

 - **Paste the URL above.**

 - **Approve on the PostLake screen.** You're sent to a PostLake **Authorize** screen. Sign in and click Approve. OAuth handles it, so your agent **never sees an API key**. The agent then appears under Connected Apps in your dashboard.

## Per-agent setup

Pick your host for the exact steps. Each connects to the URL above over OAuth, so your agent never sees an API key:

 Claude Code

One command, then approve the browser page that opens:

```
claude mcp add --transport http postlake https://api.postlake.dev/mcp
```

Start a fresh session and run `/mcp` to confirm `postlake` is connected.

 Claude Desktop

Open **Settings → Connectors → Add custom connector**, paste the server URL, and approve the browser sign-in. PostLake's tools then appear in any chat.

 Cursor

Open **Settings → Tools & MCP → New MCP server** (this opens `mcp.json`), merge this in, and save:

```
{
  "mcpServers": { "postlake": { "url": "https://api.postlake.dev/mcp" } }
}
```

Then connect it under **Settings → Tools & MCP** and approve the sign-in.

 ChatGPT

In ChatGPT's developer mode / custom connectors, add a new MCP server pointing at the URL above, then approve the sign-in.

 Gemini CLI

```
gemini mcp add postlake https://api.postlake.dev/mcp
```

Then approve the browser page to authorize.

 VS Code · GitHub Copilot

In Copilot **Agent mode → MCP servers → Add**, point it at the URL above and sign in.

 Any other MCP host

Point its “add MCP server” action at `https://api.postlake.dev/mcp` with no `Authorization` header. OAuth signs you in through your browser.

## The toolset

Once connected, the agent gets a focused set of tools. Everything it needs to post and reason, and nothing it doesn't (account setup and connecting stay in your dashboard). One normalised response shape throughout:

| Group | What the agent can do |
| --- | --- |
| **Publish & schedule** | Post now or for later; edit or cancel anything queued. `create_post`, `edit_post`, `cancel_post` |
| **Discover & validate** | Read each platform's real limits and options, and dry-run a post before sending it. `get_platform_capabilities`, `validate_post`, `get_publish_info` |
| **Channels & media** | See the accounts and profiles you've connected, and upload media from a URL. `list_social_accounts`, `list_profiles`, `upload_media` |
| **Analytics** | Per-post and cross-platform performance, to decide what to post next. `get_analytics`, `get_post_analytics` |
| **Safe by default** | Idempotent retries mean a retrying agent never double-posts, even at 3am. |

## What it looks like in use

Once connected you can just say:

```
"Post this photo to Instagram and LinkedIn, schedule a follow-up
for Friday at 9am, and tell me which of last week's posts did best."
```

## Security & revoking access

Agents authorise over OAuth, so an API key is never exposed to the model or pasted into a chat. Every agent you authorise is listed under **Connected Apps** in your dashboard, click **Revoke** next to any one to cut off its access immediately; it would need to re-authorise to return.