X (Twitter) posts with Claude and Bolta
Draft and schedule social posts by chatting with Claude. Parts of the Claude route are not confirmed yet, and the note below says which. Nothing goes live on X until you say yes.
Partly confirmed, see what is and is notChecked 2026-11-21
You sign in with your Bolta login in a browser window and tick which brands Claude may reach.
Draft an X post of 280 characters or fewer announcing our new feature, and show me the count
Illustration of the reply: Bolta returns a draft showing the connected account and the scheduled time, with Approve, Edit and Reject actions.
What is and is not confirmed
Read this before you set up Claude
- Confirmed from Anthropic's help pages: custom connectors that use a remote MCP server are available on Claude's Free, Pro, Max, Ultra, Team and Enterprise plans, and Free allows one custom connector.
- Confirmed from Anthropic's help pages: skills can be uploaded as a ZIP of a folder that holds a SKILL.md file.
- Not confirmed: Bolta has not run the claude.ai, Claude Desktop or Cowork flow end to end. Menu labels change, so look for Connectors under Customize if a name differs.
- Not confirmed: the plugin route (Customize, Plugins, boltaai/bolta-skills) comes from Bolta's own guide, not from Anthropic's help pages.
- Not confirmed: using a Bolta API key in Claude's request headers has not been tested.
What Bolta does on X
Bolta reads the limit for each connected X account, so a Premium account and a free account get different ceilings. Text that is too long does not get trimmed on X: the post fails, so the draft has to fit first.
- Single posts and threads. In a thread, Bolta posts every part after the first as a reply to the one before.
- Images. A post needs text: an image with no text is not supported on X.
X limits and format rules
Network rules last checked 2026-07-28. Bolta's posting rules for your workspace (get-posting-rules) win if they differ from this page.
Not promised for X from Claude: Polls and Spaces announcements. Neither is confirmed for Bolta. How many hashtags work best. Bolta checks none, and this page makes no claim about it.
| What to know | X's own rule | What Bolta does |
|---|---|---|
| Post length | Accounts without a paid subscription are limited to 280 characters. X Premium subscribers can publish up to 25,000. | Bolta reads the limit per account. Longer text makes the post fail, so shorten it first. The 25,000 limit is a ceiling for Premium accounts, and X can still refuse a long post. |
| Links and media | A pasted link counts as 23 characters however long it is. Photos, videos and GIFs count as zero characters. | Bolta does not check how many hashtags you use or their format. They are kept as typed. |
| Threads | Posts can be chained into a thread, and each post carries its own separate character limit. | Each X thread part after the first is posted as a reply to the one before it. |
| Who can reply | Replies can be limited to everyone, accounts you follow, verified accounts, or only the accounts you mention. It is chosen before you post. | The default is that anyone can reply unless you limit it. |
| Video | Not stated on this page. | Video on X is checked on X's side for duration, format and posting eligibility, so a successful upload does not guarantee publication. Ask for the posting rules before you attach one. |
Claude jobs for X, and how to write them
- Say what you want repeated and let Claude propose a weekly routine, which stays off until you confirm it
- Write to 280 unless the account has X Premium. Check the count, because a post over the limit fails instead of being cut.
Example prompts for X
Things to type in Claude. Each one asks for a draft and shows you the text first.
Draft an X post of 280 characters or fewer announcing our new feature, and show me the count
Which of my posts did best last month, and what should I post next?
Write a five-part X thread about how we handle onboarding, with every part inside the limit, and show me all five before saving
What is waiting for my yes in Bolta?
Bolta saves a draft, you read the exact text, you say yes
- 01
Bolta saves a draft
Claude asks Bolta for the X post in your brand voice (save-post). A saved draft is never public.
- 02
You read the exact text
On X the exact text includes the character count with links counted at 23, and, for a thread, every part in order.
- 03
You say yes
Only then does Bolta schedule or publish (publish-post), in your workspace's timezone. Safe Mode, client sign-off and brand approval rules still apply.
Using Claude for X
Parts of this route are not confirmed. The note above says which.
For X, Claude, from Anthropic, reaches Bolta through Custom connector (hosted MCP server). Sign-in: Sign in to Bolta (OAuth). The X account itself is connected inside Bolta, not in Claude.
Claude works as a chat in a browser tab or the desktop app, with Bolta added as a custom connector in your account. An X draft starts from a plain request, and Bolta holds it until you say yes.
An illustration from the Claude guide, not real output. You ask: Reply to the new comments on our last post, but let me read each one first. The reply goes along these lines: There are comments to answer. Here is a suggested reply for each, one at a time. I will send a reply only after you say yes to its exact wording. Replies drafted. Waits for your yes.
Free plans can hold one custom connector. If that slot is taken by something else, remove that connector first, because Bolta needs the slot. The skill upload gives Claude playbooks only, not the Bolta tools.
The connector is the link between Claude and Bolta. It supplies the tools for listing accounts, saving drafts and reading analytics.
Show me which brands and social accounts you can reach. This confirms the brands you ticked.
- Review what is waiting. Claude lists what is waiting for a decision. When you approve, it works from the exact text it just showed you, so what you read is what is approved.
- Campaigns from a source. Point Claude at a page or a document and ask for a run of posts around it. It plans the campaign first and waits for you before anything is saved or started.
- It learns how you write. Claude opens the voice and brand details saved in Bolta before it writes a word, so a draft starts from how your business talks.
- It checks the posting rules. Length limits and media requirements for the network are read first, so the draft is written to fit them.
- Setup: Open Connectors in Claude. Go to Customize, then Connectors. The Add button offers Add custom connector. On Team and Enterprise the Owner does this step, once, under Organization settings, Connectors, Add, Custom, Web.
- Setup: Leave the sign-in settings alone. Keep the detected sign-in settings as they are. Anthropic recommends Claude's published identity for the OAuth client. Do not add request headers, then click Add.
- Plugin from the boltaai/bolta-skills marketplace. Described only in Bolta's own guide, for paid plans. Anthropic's skills article does not cover marketplace steps, and Bolta has not tested this in the chat.
- Posts you approved with a date and time stay scheduled in Bolta and go out at that time without a Claude chat open.
- Skill upload. Choose this if you are on Free. You still need the connector, because the skill brings playbooks and not tools. Download the skills/bolta folder, zip it so the bolta folder is the top item, then upload it under Customize, Skills, Create skill, Upload a skill. Anthropic documents this route on every plan, and Enterprise Owners must switch Skills on first.
Connect Claude to Bolta
You sign in with your Bolta login in a browser window and tick which brands Claude may reach.
X questions, answered for Claude
- What happens if Claude writes an X post that is too long?
- The post fails. Bolta does not trim X text, so Claude has to shorten it first. The limit is 280 characters for accounts without a paid subscription, and X Premium accounts can post up to 25,000, though X can still refuse a long post.
- Can Claude write an X thread?
- Yes. Ask for several parts, and Bolta posts each part after the first as a reply to the one before it, so they read as one thread. Each part carries its own limit. You read all of the parts in Claude and say yes before any of them goes out.
- Do I need an API key?
- Not for the normal sign-in. A Bolta API key can go in request headers as an alternative, but Bolta has not tested that in Claude and Anthropic reviews custom header names.
- Is it safe to add a custom connector?
- Anthropic does not verify custom connectors, so only add addresses you trust. Bolta's server address is https://mcp.bolta.ai/mcp, and Claude can reach only the brands you ticked and only what your role allows.
- Can Claude see my posting history and results?
- Yes, for the brands and accounts you ticked, as far as your Bolta role allows. Claude can read analytics and your recent posts to suggest what to write next. These are read-only requests and change nothing.
- A brand is missing from what Claude can see
- A connection reaches only the brands you ticked. Reconnect Bolta and tick the missing brand. With several brands, name the brand in your request so Claude does not have to guess.
- Does Claude publish X posts without my yes?
- No. Nothing is approved, scheduled or published until you say yes to that X post. Whether Claude completes the connection is not fully confirmed, so read the note above first.
More from Claude
Claude can work with the other networks Bolta publishes to. Each page has its own limits and review notes.
X from other AI agents
The same X limits apply whichever agent asks. The connection and the setup are what change.
Try an X draft from Claude
Connect Claude, ask for an X draft and read the exact text. Nothing goes live until you say yes.