How to connect Buttondown MCP to Claude Desktop
Add this block to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows), then restart Claude Desktop. Cursor and Codex use a similar schema.
{
"mcpServers": {
"buttondown": {
"command": "npx",
"args": ["-y", "<server-package-name>"],
"env": {
"BUTTONDOWN_API_KEY": "your-api-key-here"
}
}
}
}
// Server source: https://github.com/The-Focus-AI/buttondown-mcp
// Check the server's README for the exact "command" and required env vars.Some MCP servers require an API key. Check the source page for setup: github.com/The-Focus-AI/buttondown-mcp.
Does Buttondown MCP cost extra?
The Buttondown MCP server is community-built — free to run, but you still pay for your Buttondown subscription.
- Community MCPs are normally self-hosted from a GitHub repo. There's no extra license fee.
- Your Buttondown account still needs whatever plan is required to access the data the MCP server queries.
- Trade-off: zero MCP cost, but no guarantee it'll keep working when Buttondown changes their UI or API.
Buttondown subscription pricing
| Plan | Monthly | Annual / mo |
|---|---|---|
| Free | Free | Free |
| Basic | $9 | $7.5 |
| Standard | $29 | $24.17 |
| Professional | $79 | $65.83 |
| Advanced | $139 | $115.83 |
Source: buttondown.com/pricing. Scraped 2026-05-19.
Buttondown also publishes a REST API
Buttondown publishes an API, but per-tier gating wasn't extracted automatically.
See Buttondown API pageWhat you can do with Buttondown from an AI agent
Three shapes of agent workflow. Pick the row that matches how you actually use Claude / Cursor / Codex day to day.
Skip the dashboard, ask Claude
- "What campaigns underperformed this week?" answered in seconds
- Quick one-off questions without leaving the editor
- Pipe Buttondown data into your personal notes / docs without writing a script
Run client analysis at agent speed
- Hand the MCP server to your team — every consultant can ask Claude about any client's Buttondown account
- Multi-account workflows without context-switching the Buttondown UI
- Reports you'd normally spend hours on, done before standup
Production agent workflows
- Embed in your internal Codex / Cursor agents that triage Buttondown data daily
- Combine with other MCP servers in a multi-step agent chain
- Constrain agents to read-only roles to keep production Buttondown safe
Limits and gotchas
- Community MCP — not maintained by Buttondown. Check the README and last-update date before depending on it.
- Fallback: the REST API works for any flow the MCP server doesn't cover.
- Auth flow: MCP servers usually inherit the underlying API auth method (unknown). Expect to configure that on first install.
- Rate limits: MCP calls count against your underlying Buttondown API quota. Burst usage from a curious agent can drain a daily allowance fast.
Agent-readiness verdict
Minimal agent fit: community MCP exists and public API docs are available, but no official MCP hosting, OpenAPI spec, or SDKs limit integration depth. The lack of webhooks and structured outputs means agent workflows will struggle with real-time syncing and reliable data parsing.
Scored 2026-05-19 by Joonas (TMB).
Buttondown MCP & API FAQ
Is the Buttondown MCP server official?+
Can I use the Buttondown MCP with Cursor or Codex?+
Does Buttondown have a public API?+
Sources
- Buttondown official site: https://buttondown.com
- MCP server page: https://github.com/The-Focus-AI/buttondown-mcp
- API docs: https://buttondown.com/api
- Pricing source: https://buttondown.com/pricing (scraped 2026-05-19)
Data verified by Joonas on the dates shown. MCP server status auto-rechecked weekly.

