Claude + Mastodon

Mastodon 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 Mastodon until you say yes.

You sign in with your Bolta login in a browser window and tick which brands Claude may reach.

ClaudeBolta connected
You

Tell me the character limit for my Mastodon instance, then draft a post about our new release inside it

Illustration of the reply: Bolta returns a draft showing the connected account and the scheduled time, with Approve, Edit and Reject actions.

Illustration. Your drafts show your real text, account and time.

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.
Bolta on Mastodon

What Bolta does on Mastodon

The text limit on Mastodon is set by your own instance, and Bolta reads it for the connected account instead of using one fixed number. The usual limit is 500 characters.

  • Text posts, within the limit your instance sets.
  • Public posts by default, or another visibility if you set it.
Limits and format

Mastodon limits and format rules

Bolta's posting rules for your workspace (get-posting-rules) win if they differ from this page.

Not promised for Mastodon from Claude: Polls, threads and instance-specific features. None is confirmed for Bolta. Any rule from a particular instance. Each instance sets its own, so check yours.

Mastodon limits and format rules
What to knowMastodon's own ruleWhat Bolta does
Post lengthNot stated on this page.Set by your instance. Bolta reads it per account, and the usual limit is 500. Text over the limit is trimmed back to the last whole sentence or word that fits.
VisibilityNot stated on this page.Public unless you set another visibility.
FormattingNot stated on this page.Mastodon posts are plain text here. Markdown is flattened, and #hashtags and @mentions stay as typed.
Finding conversationsNot stated on this page.Hashtag-based. The query is folded into a single tag, because full-text status search is unavailable on most instances.
Best practices

Claude jobs for Mastodon, and how to write them

  • Open Claude on the desktop app each Monday and ask what is waiting for your yes, then approve the ones you choose after Claude shows you the text
  • Ask for your instance's limit before drafting. It differs from instance to instance.
Prompts

Example prompts for Mastodon

Things to type in Claude. Each one asks for a draft and shows you the text first.

Tell me the character limit for my Mastodon instance, then draft a post about our new release inside it

Which of my posts did best last month, and what should I post next?

Draft a Mastodon post that is visible to everyone, and show me the text before saving it

Draft a Mastodon post with two hashtags and show me exactly how they will appear

Review

Bolta saves a draft, you read the exact text, you say yes

  1. 01

    Bolta saves a draft

    Claude asks Bolta for the Mastodon post in your brand voice (save-post). A saved draft is never public.

  2. 02

    You read the exact text

    On Mastodon the exact text includes its visibility, because the default is public, and where the limit for your instance would cut it.

  3. 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.

Claude and Bolta

Using Claude for Mastodon

Parts of this route are not confirmed. The note above says which.

For Mastodon, Claude, from Anthropic, reaches Bolta through Custom connector (hosted MCP server). Sign-in: Sign in to Bolta (OAuth). The Mastodon 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. A Mastodon 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: What is waiting for my yes in Bolta? The reply goes along these lines: You have 4 drafts waiting. I can read any of them out in full. Name the ones to approve and I will repeat the exact wording back before I approve them. Nothing approved. Waits for your yes.

Claude Free allows a single custom connector in all. If another connector holds that slot, Bolta cannot be added next to it.

What is waiting for my yes in Bolta? This only reads, and it shows the connection works.

Plan a weekly routine for me and do not save it yet. This shows how plans work before you commit to one.

  • Voice and brand. Before writing, Claude reads the voice and brand details held in Bolta. If none exist yet it can draft them from your website and show you the result first. Voice profile changes are also shown to you before they are saved.
  • Replies to comments. Claude can look through engagements and draft a reply for you to read. A reply is sent only after you say yes to its exact wording.
  • It shows you the text and saves a draft. The draft is stored in Bolta as a draft, never as a live post. You can edit it in the chat or in the Bolta app.
  • You say yes, or ask for changes. Approval, scheduling and publishing happen only after you confirm the exact text in your next message. A reply asking for changes leads to a revised draft.
  • Setup: Check what you need. A Bolta account with at least one brand, and a Claude account. Claude Free works but allows only one custom connector in total. Sign-in happens in a browser window.
  • Setup: Add the Bolta skill. Tools and playbooks arrive separately: the connector supplies the tools, and the skill tells Claude in what order to use them. Paid plans can add the plugin from the boltaai/bolta-skills marketplace under Customize, Plugins. Any plan can zip the skills/bolta folder and upload it under Customize, Skills. Skip this step if you already have the plugin.
  • Hosted MCP with sign-in (OAuth). Add https://mcp.bolta.ai/mcp as a custom connector under Customize, Connectors. Anthropic documents custom connectors on every plan. Bolta's own repository lists claude.ai as not tested end to end, so run the check prompt after setup.
  • Routines you confirmed run on Bolta's side. Claude is only where you set them up.
  • Plugin from the marketplace. Choose this if you are on a paid Claude plan and want updates to arrive on their own. Bolta's guide says the plugin needs Pro, Max, Ultra, Team or Enterprise. In Customize, Plugins, add the marketplace boltaai/bolta-skills and then the bolta plugin. This route comes from Bolta's guide and has not been tested end to end.
Connect

Connect Claude to Bolta

You sign in with your Bolta login in a browser window and tick which brands Claude may reach.

FAQ

Mastodon questions, answered for Claude

What is the Mastodon character limit for a post from Claude?
It depends on your instance. Bolta reads the limit for the connected account, and the usual limit is 500 characters. Anything over it is trimmed back to the last whole sentence or word.
Are Mastodon posts from Claude public?
Yes, unless you set another visibility. Say who may see the post when you ask, and check it when you read the draft.
Can Claude post without asking me?
Not by default. Drafts are free to save, but approving, scheduling, publishing, replying and deleting need your yes in the chat. Bolta has a setting that lets a connected AI app publish its own posts, so check that it is off in your Bolta workspace if you want every post to wait for you.
Can I connect several brands?
Yes. A connection covers one organization and the brands you tick on the consent page. If you tick several, say which brand each request is for.
How do I change or fix the connector later?
Remove it and add it again, which is Anthropic's way of editing a custom connector. Then sign in and tick your brands again.
The sign-in window loops and Claude keeps asking me to connect
Finish the sign-in in the browser where you are logged in to Bolta. If it still loops, remove the connector and add it again with the exact address https://mcp.bolta.ai/mcp. Anthropic says to edit a connector by removing it and adding it again.
Does Claude publish Mastodon posts without my yes?
No. Nothing is approved, scheduled or published until you say yes to that Mastodon 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.

Mastodon from other AI agents

The same Mastodon limits apply whichever agent asks. The connection and the setup are what change.

Try a Mastodon draft from Claude

Connect Claude, ask for a Mastodon draft and read the exact text. Nothing goes live until you say yes.