Post to social media from your AI agent
PlanVortex is a social media publishing platform with a public API and an official MCP server. An agent can schedule posts, read the comment inbox and answer direct messages across all your social networks, and ask our planner to write the whole week. In Claude it connects from the connector directory with nothing to install; anywhere else it is one command, with your own account's credentials.
npx -y planvortex-mcpThe official MCP server. Nothing to install: your AI client starts it.In Claude you only need your PlanVortex account. To run it on your machine you need a PlanVortex app, and every plan has them: 1 on Free, 2 on Basic, 5 on Pro and up to 10 on Custom. You do not have to pay to connect an agent.
In Claude's connector directory, and published in the official MCP registry, on Glama and on Smithery.
What an agent can do with PlanVortex
Thirty-one tools, grouped by what they act on. Twenty-two read and nine write. The thirty-second, create_ai_plan, is not in the list until you switch it on, because it spends AI credits from your account.
| Group | Tools |
|---|---|
| Context | list_organizationslist_accountsget_plan_useget_unread_counts |
| Publishing | list_publicationsget_publicationlist_destinationscreate_publicationupdate_publicationretry_publication |
| AI planner | get_planner_templateslist_store_productslist_ai_plansget_ai_planget_ai_plan_results(create_ai_plan) |
| Media | upload_media |
| Comments | list_commentsget_comment_threadreply_to_commenthide_commentmark_comment_read |
| Messages | list_conversationslist_messagessend_message |
| Numbers | get_dashboard_summaryget_publication_statsget_top_publicationsget_account_metrics |
| Catalog | get_social_limitsget_social_capabilitiescreate_connect_link |
On top of that: three ready-made prompts (weekly_plan, inbox_triage and publish_from_brief) and four resources carrying each network's limits, its capabilities, the comment matrix and your organizations. The differences between networks travel as data, so the model never has to guess what each one allows.
Supported networks
Facebook, Instagram, Threads, LinkedIn, TikTok, X, WhatsApp, YouTube, Bluesky, Discord, Telegram, Slack and Pinterest. All of them publish except WhatsApp, which is messaging, so there the agent reads, replies and measures. Slack is the other way round: it publishes and it measures, but it has no comments and no direct messages, because it is a team channel and not an audience. Pinterest publishes and measures but has no comments either (its API does not provide them), and every pin goes to a board: the agent lists them with list_destinations and picks one on each post.
The call that writes the week
Almost every social media MCP server lets the model write the copy itself. This one does not need to: PlanVortex has its own planner, and an agent can ask it for a full week built from a theme, from your own photos, from an article or from your shop's catalogue.
> Plan the week for the bakery: sourdough bread, use my August photos and post it to Instagram and LinkedIn. get_planner_templates() → from_images: 0 image credits · 7 posts create_ai_plan({ template: "from_images", accounts: [...] }) → budget: 350 credits · status: pending get_ai_plan(plan) // minutes later → generated · 7 drafts with copy and photo
Generating takes minutes and is not a single call: create_ai_plan queues the plan and returns the budget, get_ai_plan is polled until it finishes, and what comes out are drafts. Scheduling them is still your call, one post at a time.
The cost is known before anything is generated
The server works out what the plan costs and returns it when queuing. A plan that does not fit your credits is rejected whole instead of half-generated, so an agent stuck in a loop cannot drain your account without you seeing it.
And you switch it on, with one line
create_ai_plan is the only tool that spends money, so it is registered only with PLANVORTEX_MCP_ALLOW_AI=1 in your configuration. Switched off it does not even appear in the tool list: there is no way to call it. A person writes that line once, before any agent starts.
Five templates, and two spend no images
get_planner_templates publishes all five with what each one costs, so the agent can explain the price before asking your permission. The ones that start from your own photos or your catalogue spend no image credits at all.
How to install the MCP server
In Claude there is nothing to install. On your machine it takes three steps, and none of them goes through us: the server runs there, with your credentials.
In Claude, with nothing to install
In the browser, the desktop app or on your phone: open PlanVortex in Claude's connector directory, click Connect, sign in with your PlanVortex account and click Allow. No Node, no app and no client_secret, and it works on all four plans. Claude asks you to confirm before it posts, replies to or hides anything.
In Claude Code it is one line, again without credentials. Then type /mcp, pick planvortex and choose Authenticate: the browser opens the same sign-in.
claude mcp add --transport http planvortex \ https://mcp.planvortex.com/mcp
Claude acts as you, with what your roles allow in the dashboard. Three things change from the local server: social accounts are connected in the dashboard, AI plans are created there too (Claude reads them), and upload_media takes a public URL, because the server cannot see your disk.
Open PlanVortex in Claude's directory →Create an app in the dashboard
Under Settings → Apps. It gives you a client_id and a client_secret. Apps are on all four plans, so this costs nothing on the free one.
Add the server to your AI client
One command in Claude Code, or the JSON block below in Claude Desktop, Cursor and VS Code. Nothing to install: npx downloads it on start.
Ask it for something
"What do I have scheduled this week, and which comments are still unread?" If it answers with your real accounts, it works.
claude mcp add planvortex \ --env PLANVORTEX_CLIENT_ID=... \ --env PLANVORTEX_CLIENT_SECRET=... \ -- npx -y planvortex-mcp
{ "mcpServers": { "planvortex": { "command": "npx", "args": ["-y", "planvortex-mcp"], "env": { "PLANVORTEX_CLIENT_ID": "...", "PLANVORTEX_CLIENT_SECRET": "...", "PLANVORTEX_ORGANIZATION_ID": "..." } } } }
PLANVORTEX_ORGANIZATION_ID is optional and worth setting: without it, the agent spends one call per conversation working out which organization you mean.
No Node installed? Every release also ships a .mcpb bundle that Claude Desktop installs with a double click.
Download the latest .mcpb →Every environment variable
| Variable | Required? | What it does |
|---|---|---|
| PLANVORTEX_CLIENT_ID | yes | Your app's client_id. Every plan has apps. |
| PLANVORTEX_CLIENT_SECRET | yes | Its secret. Never passed as a tool argument. |
| PLANVORTEX_ORGANIZATION_ID | no | Default organization. Saves a discovery call per conversation. |
| PLANVORTEX_BASE_URL | no | Point at another PlanVortex deployment. |
| PLANVORTEX_MCP_UPLOAD_DIRS | no | Directories upload_media may read from. Empty means none. |
| PLANVORTEX_MCP_AUTH_TOKEN | with --http off-loopback | Bearer token the HTTP endpoint requires to bind anywhere but loopback. |
| PLANVORTEX_MCP_READ_ONLY | no | 1 removes the nine write tools from the listing. |
| PLANVORTEX_MCP_ALLOW_AI | no | 1 adds create_ai_plan, which spends AI credits. |
| PLANVORTEX_MCP_LOG_LEVEL | no | debug, info, warn, error or silent. Always to stderr. |
What it cannot do, and how to switch off what it can
This server puts text written by strangers (a comment, a review, a direct message) into the model's context while that same model holds tools that publish to your accounts. The limits below are the answer to that.
It deletes nothing, and that cannot be turned on
No tool deletes a post, an account or a comment. It is not an option switched off by default: the code does not exist. The worst possible case has to be something you can see and undo.
Read-only mode
With PLANVORTEX_MCP_READ_ONLY=1 the nine write tools are not registered, so they are not in the listing and the model cannot even try to call them. Twenty-two read-only tools remain.
It runs on your machine
The client_secret lives in the process your AI client starts, never on a server of ours. And if you would rather host it yourself, --http mode ships its own Dockerfile, listens on loopback only and demands a token to bind anywhere else.
It does not read your disk
upload_media only opens files inside the directories you declare in PLANVORTEX_MCP_UPLOAD_DIRS, and that list is empty out of the box. Without configuring it, the agent cannot upload a file of yours even if the model asks.
If your agent does not speak MCP, it speaks HTTP
Everything the MCP server does is also in the public API, open on all four plans, the free one included.
The API, 135 operations
OAuth 2.0 with client_credentials, JSON, and the same numbered error catalogue the libraries use. The full documentation is public.
Read the documentation →Two official libraries
npm i planvortex and pip install planvortex. Both publish with provenance and carry the token manager, file uploads and typed errors.
For developers →A node for n8n
If your agent runs inside an n8n workflow, the verified PlanVortex node publishes, uploads files and replies to comments without a single hand-written request. It uses the same app credentials.
See the node →And four files you can read without crawling anything
They sit at the site root, they are plain text and there is no JavaScript in front of them. If you are an agent evaluating this tool, start here.
/llms.txtWhat PlanVortex is, who it is for, with verified prices/llms-full.txtThe whole API in plain text: all 135 operations with their parameters/openapi.jsonThe complete OpenAPI, to generate a client in any language/pricing.mdThe tariff, in markdown, with no form to fill in
Frequently asked questions
What is the PlanVortex MCP server?
It is the official Model Context Protocol server connecting an AI assistant to your social media accounts. It gives thirty-one tools to schedule posts, read comments, answer messages and pull metrics across all your social networks. It installs with npx and runs on your machine with an app's credentials, or, in Claude, connects from the connector directory with your PlanVortex account.
Do I need a paid plan to connect an agent?
No. The apps that give you the credentials are on all four plans, the free one included, which comes with 1 app, 2 connected accounts, unlimited posts and 1 GB of storage, no card required. What changes with the plan is how many separate apps you get and the call rate.
Which social networks can an agent publish to?
Facebook, Instagram, Threads, LinkedIn, TikTok, X, YouTube, Bluesky, Discord, Telegram, Slack and Pinterest. You do not publish on WhatsApp: it is messaging, so there the agent reads, replies and measures.
Can an agent delete a post or an account?
No. None of the thirty-two tools deletes a post, an account or a comment, and it is not an option left switched off: that code does not exist in the server. It is the only serious guarantee you can give a model that reads strangers' text while holding the ability to publish in your name.
Where does my client_secret end up?
In the process your AI client starts, on your machine. It never goes through a server of ours and it is never passed as a tool argument, so it does not end up in the conversation history or in the model's context.
Can the agent write the content, not just schedule it?
Yes, and the model does not write it: the PlanVortex planner does, from a theme, your own photos, an article or your shop's catalogue. Generating spends AI credits, so that tool has to be switched on by hand with PLANVORTEX_MCP_ALLOW_AI=1. What comes out are drafts.
Does it work with Claude Desktop, Cursor and VS Code?
Yes. In Claude (browser, desktop app and phone) it is in the connector directory: you sign in with your PlanVortex account and install nothing. Claude Code takes one command, and Cursor and VS Code take the same JSON block in their MCP servers file.
What if my agent does not use MCP?
Then it uses the public HTTP API: 135 operations over OAuth 2.0, open on all four plans. There are official Node and Python libraries, the complete OpenAPI published at the site root, and a plain-text version of the documentation meant to be read by a model. And if it works inside n8n, there is a verified node: n8n-nodes-planvortex.
One command, and your assistant publishes
Create an app on the free plan, paste the two credentials into your AI client and ask it what you have scheduled this week. No card required.