How postmakr works.

From idea to published post: this page explains the system behind postmakr, including the MCP connection and the complete tool reference for your AI model.

What is postmakr?

postmakr is a content platform that turns whatever moves your industry into finished social posts: carousels, reels and stories for Instagram and TikTok. The special part: postmakr doesn't ship its own AI model. Instead it works through the open Model Context Protocol (MCP) with the model you already use: Claude, GPT, Gemini or any other.

Every brand gets its own workspace. That's where its style guide, feeds, post archive and learnings live, everything your AI model needs to build posts that genuinely look like your brand. And the hardest rule in the system: nothing goes live without your approval.

How the system works

postmakr thinks in two interlocking cycles. The production loop takes posts from idea to publication, and the learning loop pulls every post's numbers back into the system.

The production loop

Radar: a scan reads your niche's feeds and rates every topic with a viral score, a ready-made hook and a format recommendation.
Topic backlog: good topics go into the queue. Nothing gets lost, even when you're busy.
Production: your AI model builds a complete post from the topic (copy, slides, rendering), grounded in your style guide and similar posts from the archive.
Approval: you see the finished draft in the dashboard, can fine-tune it in the video or post editor, and approve it or send it back for revision.
Publish: the approved post goes live on Instagram and TikTok and moves into the archive.

The learning loop

Performance: views, likes, retention: every published post's metrics flow back in.
Virality diagnosis: the numbers become patterns: which hooks pull? Where do people drop off?
Learnings: the insights feed the next scan and the next production as rules. Every post makes the next one better.

The features in detail

Topic radar

The radar is where everything starts. It regularly reads your niche's feeds (trade media, news sources and industry blogs, whatever is configured in your workspace) and distills them into concrete post suggestions. Each suggestion arrives ready-thought-out, not as a bare link: with a viral score estimating its reach potential, a fully written hook as a possible opener, and a recommendation for the best-fitting format.

In the dashboard you sift the suggestions, move the good ones into the topic backlog and discard the rest. That builds a queue of pre-qualified ideas, and postmakr works through it on its own: the engine automatically produces the posts from the backlog, and all that's left for you is the approval.

Virality filter

Not every relevant topic is a good social topic. The virality filter scores every idea against criteria defined in your workspace: whether the topic creates clear personal stakes, whether it can be sharpened into one sentence, whether it can be told visually. What won't pull gets dropped before any production time flows into it.

The filter gets sharper over time: insights from the learning loop, which hooks pulled and where people dropped off, flow back into the scoring as rules. You can adjust your virality criteria in the settings at any time.

Every format, fully editable

postmakr produces against a format catalog: carousel, animated carousel, reel, story or sharepic. Each format brings its own spec for structure, slide count and dramaturgy. The AI model doesn't freestyle; it builds along that spec so every post hits your brand's style.

Finished doesn't mean frozen: every post stays fully editable until approval. The video editor brings a full-featured timeline with video, text and audio tracks, and the post editor opens every slide as real layers: you can grab text, images and shapes right in the browser. Export happens server-side at full resolution, up to 4K.

Your own AI model

postmakr deliberately ships no AI model of its own. Instead, the model you already pay for (Claude, GPT, Gemini or any other) connects to your workspace through the open Model Context Protocol. That has three advantages: you pay no duplicate AI costs, your content runs through your own account, and you decide which model you trust.

postmakr stores no third-party API keys. The connection runs over a workspace-scoped access key that you generate in the dashboard and can revoke at any time. How the connection works technically is covered in Understanding MCP.

Team workspaces

Every brand lives in its own workspace with its own style guide, feeds, archive and learnings. Nothing mixes. An agency can run ten client brands in parallel without one brand's tone leaking into another's posts.

Within a workspace, several people work together: each access has its own key, produces with its own AI account, and only sees the workspaces that concern them. Approval remains a clearly defined step: whoever may approve, approves; everyone else contributes.

Performance learning

After publishing, the second half of the system kicks in. Every post's metrics (views, likes, comments, shares, drop-off points) flow back into the workspace and get condensed into patterns in the virality diagnosis: which hook types pull with your audience? Which formats perform? On which slide do people bail?

The patterns become learnings, and those land exactly where the next production starts: in the context your AI model receives on its next /scan and /create. The system gets a bit sharper with every published post, not as a black box, but readable in the dashboard.

Understanding MCP

The Model Context Protocol is an open standard that gives AI models a uniform way to talk to external systems, often described as "USB-C for AI applications". Instead of building a custom integration for every tool, your AI model connects once via MCP and can then use everything the server offers.

postmakr is such an MCP server. Your AI model (the MCP client, e.g. Claude in the terminal or in the app) connects to your workspace and gets three things:

Tools: actions the model can perform: scanning, saving drafts, rendering slides, starting workflows. All 16 are listed in the reference below.
Context: your brand's style guide, format catalog, archive and learnings, so the post sounds like you.
Workflows: guided sequences like /scan or /create that walk the model through production step by step.

Your AI model produces into your postmakr workspace via MCP. You review the result and approve it, and only then does the post go to your networks.
All trademarks and logos are the property of their respective owners. No partnership implied.

The most important difference to other platforms: AI production runs on your model and your plan. postmakr provides knowledge, tools and quality control and stores no third-party API keys.

Tool reference

Your workspace exposes these 16 tools to the connected AI model via MCP. You don't need to memorize them, because your model picks them itself. But they show exactly what the system can do.

Context & archive

`get_workspace_context`	Returns the workspace overview: brand, style guide, format catalog and current learnings.
`get_reference_posts`	Finds the two or three most similar already-published posts for a topic, as a style template for the new one.
`archive_search`	Searches the entire post archive by topic, hook or format.

Radar & topics

`run_scan`	Runs the niche feed scan and collects fresh raw data.
`get_scan_results`	Returns the latest scan evaluation with rated topic suggestions.

Drafts

`list_drafts`	Lists all current drafts with their files.
`save_draft`	Saves a file into a draft: copy, slides, captions.
`read_draft`	Reads a file from a draft, for example to revise it.

Rendering

`render_slide`	Renders a slide to a finished PNG at post resolution.
`start_animation_render`	Starts rendering an animated slide as a video (MP4).
`check_render_status`	Checks the status of a running video render.

Workflows

`start_scan_review`	Starts the guided scan review: sift topics, rate them, move them into the backlog.
`start_create`	Starts the guided production of a post from a topic, including format spec and references.
`start_revise`	Starts revising an existing draft based on your feedback.
`start_approve`	Starts the approval check: final quality control before publishing.
`approve_post`	Archives the approved post and readies it for publishing.

Security & data

postmakr is built for brands that take their content seriously. A few hard principles apply:

Strictly separated workspaces: every brand lives in its own isolated data area. Nobody sees another brand's drafts, archive or numbers, not even by accident.
One central login: sign-in runs through a dedicated, self-hosted identity service (Keycloak). Your account belongs to you, and passwords never touch the application itself.
No third-party API keys: your AI model runs on your own account. postmakr stores no third-party keys, only the workspace access key that you generate yourself and can revoke at any time.
Hosted in Germany: the platform runs on servers in Germany, with daily backups of all workspaces.
Your content is yours: everything created in your workspace (posts, media, learnings) remains your property and can be exported at any time.

Frequently asked questions

Do I need my own AI subscription?

Yes. postmakr deliberately ships no AI model of its own and works with the subscription you already have (Claude, GPT, Gemini or any other). That way you pay no duplicate AI costs, and your content runs through your own account.

Do I need the AI for editing and exporting?

No. The dashboard and the editors work entirely without AI: you can edit posts by hand and export them with one click. Rendering is done by the server, whether you trigger it in the dashboard or your AI model triggers it via a tool.

Can my team work with me?

Yes. A workspace can have several accounts: each person works with their own login and their own AI account on the same brand, with clear approval paths.

Does postmakr publish to Instagram and TikTok automatically?

During the beta you export the finished post and upload it yourself. Direct publishing with automatic feedback of views and likes is in the works and will arrive as an update during the beta.

What does postmakr cost during the beta?

Nothing. During the beta phase you test everything for free. Fair pricing comes afterwards, and early testers get special conditions.

Connect & get started

The connection takes just a few minutes to set up:

1. Create a workspace: sign up, describe your brand, and your feeds and style guide get set up.
2. Generate an API key: in the dashboard under "Connection & API keys" you create a key for your workspace.
3. Connect your AI model: add the postmakr MCP server in your AI client, for example in Claude Code in the terminal, or as a connector in the app. The step-by-step guide for all clients is on the MCP page. From then on your model has all the tools and your brand context.
4. Produce: /scan fetches fresh topics, /create has your model build the post. The final approval is always yours, in the dashboard.

Team workspaces: every workspace can have several API keys. Colleagues work on the same brand with their own AI accounts, with clear approval paths.