Most newsletter work is repeatable: gather the week's stories and events, write them up in the publication's voice, check the facts, and get a clean draft into the email platform. lightbreak already does each of those steps for people. Now an AI agent can do them too, using the same rules, the same section instructions and the same fact-checking review.
What an agent can do
Newsletters and issues
- See every newsletter, start or generate an issue, read it section by section, delete it.
list_publications · list_issues · list_templates · create_issue · generate_issue · get_generation_status · get_issue · get_issue_tree · delete_issue
Finding content
- Browse the stories, events, jobs and places lightbreak already collected, read any link, manage sources.
browse_content · browse_places · read_link · list_sources · add_source
Writing and editing
- Have lightbreak write in each section's voice, add your own stories, events and jobs, edit or remove anything.
write_story_for_section · add_story · add_event · add_job · update_block_text · update_issue_details · remove_blocks · save_issue_tree · upload_image_from_url · suggest_subject_lines · write_intro
Checking and finishing
- Fact-check every link, image, claim and sentence, then export or push a draft to the ESP.
review_issue · get_review · export_issue_html · push_to_beehiiv · push_to_activecampaign · mark_issue_done
Notifications
- Get told the moment a draft is ready, a review finishes, or a draft reaches the ESP.
add_notification · list_notifications · test_notification · remove_notification
Built for creating, not sending
Every action goes through the same checks a person's clicks do: workspace access, save conflicts and the AI spend limit.
- 35
- ActionsFrom finding a story to pushing the draft
- 4
- Review checksLinks, images, facts and copy
- 5
- NotificationsSigned, retried, logged
- 0
- Emails sentA person schedules every send
How a week's issue can run
- 01
Build. The agent pulls this week's stories, events and restaurants that lightbreak already collected, or brings its own.
- 02
Write. lightbreak writes each piece with that section's own instructions and voice, exactly as when a person drags a story in.
- 03
Review. The reviewer opens every link and source and checks each claim. The agent fixes what it flags and runs it again.
- 04
Draft. The finished issue goes to Beehiiv or ActiveCampaign as a draft, and your notification tells your team it's ready.
We build the issue. Your platform sends it.How lightbreak works, for people and agents alike
Connect your agent
- 01
In lightbreak, open Settings, then AI agents & API, then New key. Name it after the agent. Copy it right away: it's shown once.
- 02
Give the agent the address
https://app.lightbreak.ai/api/mcpand the headerAuthorization: Bearerfollowed by the key. - 03
Ask it: "List my lightbreak newsletters." If it answers, you're connected.
Claude Code terminal, Claude desktop app, Conductor
Run once, with your key in place of the placeholder:
claude mcp add --scope user --transport http lightbreak https://app.lightbreak.ai/api/mcp --header "Authorization: Bearer lbk_YOUR_KEY"Codex OpenAI
Add to ~/.codex/config.toml:
[mcp_servers.lightbreak]
url = "https://app.lightbreak.ai/api/mcp"
http_headers = { Authorization = "Bearer lbk_YOUR_KEY" }OpenCode opencode.json
Keep the key in its own private file and point to it:
"mcp": {
"lightbreak": {
"type": "remote",
"url": "https://app.lightbreak.ai/api/mcp",
"headers": { "Authorization": "Bearer {file:~/.secrets/lightbreak.key}" }
}
}Cursor, Windsurf and other MCP apps remote MCP server
Add a remote (HTTP) MCP server with the address https://app.lightbreak.ai/api/mcp and the header Authorization: Bearer followed by your key.
Grok, Meta Muse, ChatGPT and custom agents MCP, actions or plain HTTPS
If it asks for an MCP server, use the address and header above. If it asks for an OpenAPI or "actions" link, use https://app.lightbreak.ai/api/agent/openapi with the same key. Anything that can send a web request can call an action directly with POST https://app.lightbreak.ai/api/agent/<action>.
What a key can and can't do
Can
- Everything a newsletter manager does day to day, including deleting issues and pushing drafts, inside the one workspace the key belongs to (or only the newsletters you pick).
Can't
- Manage people or other keys, open lightbreak's screens, reach another workspace, or send email.
Questions people ask
- Is it safe to give an AI a key?
- A key only works inside one workspace, can't manage people or other keys, and can be switched off in one click. lightbreak keeps a fingerprint of the key, never the key itself.
- Can an agent send my newsletter?
- No. lightbreak doesn't send email. The furthest an agent can go is putting a draft into Beehiiv or ActiveCampaign, where a person schedules it.
- Will it overwrite what my team is editing?
- No. If someone saved the issue in the meantime, the agent's save is refused with a clear conflict instead of replacing their work.
- Does the AI make things up?
- That's what the review is for. It opens every story's source, checks each claim, and only calls something wrong when it can quote the source that proves it.
- What does it cost?
- Connecting is free. Writing, generating and reviewing use AI the same way they do when a person clicks the button. A full review is a few cents per issue.