Creator, Studio and Agency plans from $19/mo, each with a 7-day free trial. Start your trial
by Phronesis AI Lab
MCP server

Schedule your social from Claude or ChatGPT

Connect Social Digital Marketer over the Model Context Protocol and run your scheduling from a conversation. Check your calendar, schedule or queue posts across every account, read post analytics and clear approvals, with your workspace rules intact.

What the assistant can do

Schedule, queue and report in a conversation

The same scheduler the app runs, reachable from your AI assistant. You write the posts; it handles the calendar.

Read post analytics

Ask "what were my top posts this month?" and the assistant pulls real numbers from Social Digital Marketer: reach, engagement and clicks per post.

Schedule and queue

Hand over a post you wrote and a time, or drop it into each account's next queue slot. Reschedule or pull a post without opening the app.

List accounts and the calendar

See which accounts are connected and healthy, what is scheduled this week, and which posts are pending, published or failed.

Approvals

List posts waiting for sign-off and approve them if your role allows. Nothing the assistant queues can skip approval.

Tool calls

Ask a question, schedule the answer

The assistant calls the MCP tools it needs, reads the data back and acts on what you asked: numbers, slots, a scheduled post. The exchange below is illustrative.

  • Reads real post analytics from your workspace
  • Schedules only what you ask; approval rules still apply
  • Scoped to the workspace the token connects
Social Digital Marketer · connected over MCP
What was my top post this month? Schedule this one to LinkedIn and Bluesky in the next open slots.
tool call analytics.top_posts(period="30d")
↩ 3 posts · best: "We're hiring" · reach 3,589
tool call posts.queue(accounts=["linkedin", "bluesky"])
Your top post was "We're hiring" (reach 3,589). Queued your post for Thu 10:00 on LinkedIn and Fri 09:00 on Bluesky, pending approval as this workspace requires.

Your approval rules apply over MCP too

The assistant acts with the token’s permissions, nothing more. Every post it queues waits for a person with the right role to approve it. You can approve a whole week at once; the assistant cannot skip it.

Setup

Connect in three steps

From a token to a working conversation in a few minutes.

Get your MCP token

Open Social Digital Marketer, go to developer settings and create an MCP token for the workspace you want to connect. The same key works for the API and the CLI.

Add the server

In Claude or ChatGPT, add the MCP server with the URL and your token. The client discovers the available tools automatically.

Start a conversation

Ask what is scheduled, queue a post or check last week’s numbers. Anything the assistant queues waits for a person to approve it.

MCP FAQ

Questions about MCP

Which assistants can connect?

Any MCP-capable client. In practice that means Claude and ChatGPT today, with more clients as they adopt the Model Context Protocol. The Social Digital Marketer MCP server is in beta.

Does the assistant publish on its own?

No. It only queues what you ask it to, with the permissions of the token you gave it, and everything queued over MCP waits for a person with the right role to approve it before it publishes.

Does the MCP server write posts for me?

Your assistant does the writing; the MCP server schedules, queues and reports on those posts. AI drafting in your brand voice inside the product is in limited availability, switched on per workspace, and everything still waits for a person to approve it.

Which plans include MCP?

The Studio and Agency plans, alongside the REST API, SDKs and CLI. Both start with a 7-day free trial.

What data can the assistant see?

Only the workspace the token is scoped to: its accounts, calendar, queue and post analytics. It cannot reach other workspaces, and it cannot skip approval.

How is this different from the API and CLI?

The API is for your own code and the CLI is for your terminal and scripts. The MCP server is for AI assistants: it exposes the same actions as tools an assistant can call in a conversation, so you schedule by chatting instead of writing requests.

Run your scheduling from a conversation

The MCP server is open during the beta. Your approval rules come with it.