Mastodon posts with DeepSeek and Bolta
Use a DeepSeek model as the drafting brain, with Bolta holding the approval gate. Parts of the DeepSeek route are not confirmed yet, and the note below says which. Nothing goes live on Mastodon until you say yes.
Partly confirmed, see what is and is notChecked 2026-11-21
DeepSeek is the model. The Claude Code guide shows how to connect Bolta to the agent that runs it.
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.
What is and is not confirmed
Read this before you set up DeepSeek
- Confirmed from DeepSeek's own docs: its API has an Anthropic-compatible endpoint at https://api.deepseek.com/anthropic, and a guide for pointing Claude Code at it with your DeepSeek API key.
- Confirmed from DeepSeek's own docs: that endpoint ignores mcp_servers, so DeepSeek itself never holds the Bolta connection. The host agent does.
- Not found in DeepSeek's docs: any connector or MCP feature in the DeepSeek chat app, or a remote MCP setting in DeepSeek Harness.
- Not tested by us: how well Bolta's tools behave when the host agent runs a DeepSeek model. Draft quality and tool-call reliability can differ from other models, so review every draft.
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.
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 DeepSeek: 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.
| What to know | Mastodon's own rule | What Bolta does |
|---|---|---|
| Post length | Not 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. |
| Visibility | Not stated on this page. | Public unless you set another visibility. |
| Formatting | Not stated on this page. | Mastodon posts are plain text here. Markdown is flattened, and #hashtags and @mentions stay as typed. |
| Finding conversations | Not stated on this page. | Hashtag-based. The query is folded into a single tag, because full-text status search is unavailable on most instances. |
DeepSeek jobs for Mastodon, and how to write them
- Set up a recurring routine from a plan you read and confirm, instead of clicking through settings
- Ask for your instance's limit before drafting. It differs from instance to instance.
Example prompts for Mastodon
Things to type in DeepSeek. 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
What is waiting for my approval in Bolta right now?
Draft a Mastodon post that is visible to everyone, and show me the text before saving it
Summarize how my last posts performed before we plan the next batch
Bolta saves a draft, you read the exact text, you say yes
- 01
Bolta saves a draft
DeepSeek asks Bolta for the Mastodon post in your brand voice (save-post). A saved draft is never public.
- 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.
- 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 DeepSeek for Mastodon
Parts of this route are not confirmed. The note above says which.
For Mastodon, DeepSeek, from DeepSeek, reaches Bolta through Through a host agent running a DeepSeek model (Claude Code is the best documented route). Sign-in: Sign in (OAuth) in the host agent, or a Bolta API key. The Mastodon account itself is connected inside Bolta, not in DeepSeek.
DeepSeek is a model, not an app you add Bolta to. The connection lives in a host agent, such as Claude Code running a DeepSeek model, so the host saves the Mastodon draft to Bolta and Bolta keeps the approval gate.
An illustration from the DeepSeek guide, not real output. You ask: Show me my voice profile for Acme Studio, and tell me what is missing from it. The reply goes along these lines: Here is the voice profile Bolta holds. It has tone notes but no example posts you like. I changed nothing. Want me to suggest an update for you to confirm? Read only. Edits need your yes.
Whatever the agent reads from Bolta, such as brand notes and drafts, is sent to DeepSeek's API as part of the model request. Check DeepSeek's terms if that matters for client work.
Until someone tests it, we do not promise a Harness setup. Use a host agent instead.
If a Bolta call starts failing after a DeepSeek model update, check the guide first. A changed name is a cheaper fix than a changed setup.
- Review and approve on your terms. List what is waiting, read each draft, and approve only the ones you name. Approval uses the content fingerprint, so a draft edited after you read it cannot slip through.
- Campaigns from a source. Point the agent at a launch page or changelog and have it plan a short campaign. Scope and timing are confirmed separately from any post.
- DeepSeek reads your request and writes text. Claude Code sends your message to DeepSeek's Anthropic-compatible endpoint. DeepSeek decides what to say and which tool to ask for, nothing more.
- The host agent holds the Bolta connection. Claude Code keeps the MCP link to https://mcp.bolta.ai/mcp and makes the actual tool calls. DeepSeek's endpoint ignores mcp_servers, so this layer cannot be skipped.
- Setup: Pick a host agent that supports MCP. Claude Code is the best documented option for DeepSeek. DeepSeek also publishes guides for Codex, OpenCode, OpenClaw and Hermes. This page uses Claude Code.
- Setup: Add Bolta to Claude Code. Run: claude mcp add --transport http bolta https://mcp.bolta.ai/mcp. If you would rather use the plugin, the Claude Code guide on the Bolta MCP docs page has the exact commands. Do not do both, or you will have two Bolta entries.
- Hosted MCP in the DeepSeek chat app. We found no connector or MCP setting in the chat app, so we cannot show a way to add Bolta there.
- A routine you confirmed lives in Bolta and repeats without the agent open.
- The DeepSeek chat app or API on its own. Choose this if you hoped to add Bolta straight to DeepSeek. We found no connector system in the chat app, and DeepSeek's Anthropic-compatible API ignores mcp_servers. There is no verified way to add Bolta here.
Connect DeepSeek to Bolta
DeepSeek is the model. The Claude Code guide shows how to connect Bolta to the agent that runs it.
Mastodon questions, answered for DeepSeek
- What is the Mastodon character limit for a post from DeepSeek?
- 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 DeepSeek public?
- Yes, unless you set another visibility. Say who may see the post when you ask, and check it when you read the draft.
- What is DeepSeek Harness and does it work with Bolta?
- It is a plugin-based developer preview from DeepSeek. Its docs that we read do not mention remote MCP, so we do not confirm a Bolta setup there. Use a host agent for now.
- Is the DeepSeek route free?
- We do not set DeepSeek's prices, so check the DeepSeek platform. Bolta's own plans are on the pricing page. Using your key means DeepSeek bills you for model use separately.
- Claude Code still answers like its default model
- The environment variables were probably set in a different terminal. Set the variables from DeepSeek's Claude Code guide, including ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN, in the same shell you start claude from, then start it again.
- Bolta tool calls fail or come back malformed
- This is the part we have not tested. Retry once with a simple read, then try the same request on the agent's default model. If only the DeepSeek run fails, use it for drafting text and keep Bolta steps on the other model.
- Does DeepSeek publish Mastodon posts without my yes?
- No. Nothing is approved, scheduled or published until you say yes to that Mastodon post. Whether DeepSeek completes the connection is not fully confirmed, so read the note above first.
More from DeepSeek
DeepSeek 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 DeepSeek
Connect DeepSeek, ask for a Mastodon draft and read the exact text. Nothing goes live until you say yes.