Where is the source code for Postmcp Mcp Server?
The source code is linked from the repository URL on this page.
@postmcp
基本信息
Official PostMCP AI Model Context Protocol (MCP) Server. Connect your social media publishing pipelines directly into AI assistants, desktop applications, IDE workflows, and web environments like Claude Desktop , Claude.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"postmcpai": {
"command": "npx",
"args": [
"-y",
"@postmcpai/server"
],
"env": {
"POSTMCPAI_API_KEY": "pmcp_sec_your_api_key"
}
}
}
}Retrieve details of the logged-in user including subscription plan, credit balance, AI token count, the active workspace, and the caller's role in it.
List every workspace (project) the user belongs to, with the id to pass as workspaceId, the caller's role, and which one is the default. Call this first whenever the user mentions a client, brand, or workspace by name.
List every connected social profile in the workspace with the profileId needed to target it. Call this before creating a post so the post reaches the intended profile rather than every account on a platform.
Report connections whose access token has expired or is about to, and which therefore need the user to reconnect. Check this before scheduling anything far out - a post scheduled onto a dead connection fails silently at publish time.
List the workspace's brand kits: tone of voice, audience, keywords, and reference style images. Use one to keep drafted copy on-brand, and pass its id to generate_image for on-brand visuals.
Retrieve scheduled, published, draft, and failed posts, newest first, with per-profile delivery status. Every profile that received a post carries `url`, the link to the live copy - give the user that link when they ask where a post went. Returns pagination plus counts per status.
Fetch a single post by id, including per-profile delivery status, the live URL of each published copy, and the error for any profile that failed.
Dry-run a post before creating it: checks copy against each platform's character limit, flags profiles that are not connected or need reconnecting, warns when a platform requires media, reports each target's video limit when a video is attached, and reports the credit cost against the workspace balance. Costs nothing and publishes nothing. Run this before create_post whenever the copy is long, carries a link, or targets several platforms.
Schedule or immediately publish a post to specific connected social profiles. Prefer targetAccounts so the post lands only on the profiles you name. Every targeted profile becomes its own post with its own id, so each can be edited, retried or cancelled on its own - the response lists them all. With publishImmediately, each delivered profile comes back with a `url` to the live copy; pass those on to the user.
Broadcast an existing scheduled post immediately to its platforms. Also the way to retry a failed post: profiles that already received it are skipped, so only the stragglers go out. The returned post carries a `url` per delivered profile - report those links rather than only saying it published.
Cancel and delete a scheduled or failed post from the database.
Update the fields (content, target profiles, schedule date/time) of an existing post. To move a post to a different slot without touching anything else, use reschedule_post.
Move a post to a different date and time, keeping its copy and target profiles. A failed or draft post is re-armed by this and will go out at the new slot; profiles that already received it are not sent to again. Published posts and posts currently publishing cannot be moved.
Release a post left stuck mid-publish so it can be retried. Profiles that already went out keep their delivered state, so retrying afterwards will not double-post. Only use this on a post whose status is 'processing'; if it started publishing recently the call is refused unless force is true.
Generate an image for a post from a text prompt and return its hosted URL, ready to pass to create_post as mediaUrl. Pass a brandingId from list_brandings to match the workspace's visual style. Spends AI tokens.
Run several PostMCP tools in one request, in the order given. Use it whenever a task needs more than one call - scheduling a week of posts, checking accounts then publishing, or cancelling a handful of posts - instead of one round trip per call. Calls run sequentially and every tool name is validated before anything executes, so a typo cannot leave half a batch written. Cannot nest: a call inside a batch may not itself be multicall.
PostMCP AI Model Context Protocol (MCP) Server
The README includes setup instructions such as "command": "npx",.
The source code is linked from the repository URL on this page.
If the README contains a parseable MCP configuration block, it is shown in the Config tab.
OdileM2M: AI agents reach a real business by its phone number. Look the business up free, then leave a message, check open times or book a slot through Odile Direct. 50 free tasks a month per agent; lookups and availabil

LinkedIn MCP server for Claude, ChatGPT, Cursor & Codex. Read LinkedIn DMs, search your network, enrich profiles and draft messages you review before sending.
SendRaven is email infrastructure for AI agents. Send, read replies as threads, run campaigns and automations, with limits on the API key.

Send, receive and track real faxes in the US and Canada from Claude, ChatGPT or Cursor.

Official Mobile Text Alerts server. Send and schedule SMS, manage subscribers and groups, and complete carrier registration from any MCP-compatible AI assistant.
评论