Mailbuttons (mbag.ai)
Governed email for AI agents (Mailbuttons / mbag.ai): sandbox inboxes, policy gate, audit log.
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
claude mcp add --transport http mailbuttons-mbag-ai 'https://mailbuttons.com/api/v1/mcp/rpc' --header 'Authorization: <Bearer token: a scoped Mailbuttons MCP token, sent as '\''Bearer mb_sandbox_...'\'' (or mb_production_... once promoted). Get one free: sign in with an email code to get an mbk_ API key, then POST https://mailbuttons.com/api/v1/mcp/sandbox-inboxes with it. Guide: https://mailbuttons.com/developers/#mcp>'
{
"mcpServers": {
"mailbuttons-mbag-ai": {
"type": "http",
"url": "https://mailbuttons.com/api/v1/mcp/rpc",
"headers": {
"Authorization": "<Bearer token: a scoped Mailbuttons MCP token, sent as 'Bearer mb_sandbox_...' (or mb_production_... once promoted). Get one free: sign in with an email code to get an mbk_ API key, then POST https://mailbuttons.com/api/v1/mcp/sandbox-inboxes with it. Guide: https://mailbuttons.com/developers/#mcp>"
}
}
}
}
@mailbuttons/mcp-serverclaude mcp add mailbuttons-mbag-ai -e 'MAILBUTTONS_API_KEY=<your mailbuttons_api_key>' -e 'MAILBUTTONS_API_URL=https://mailbuttons.com' -- npx -y @mailbuttons/mcp-server@0.1.1
{
"mcpServers": {
"mailbuttons-mbag-ai": {
"command": "npx",
"args": [
"-y",
"@mailbuttons/mcp-server@0.1.1"
],
"env": {
"MAILBUTTONS_API_KEY": "<your mailbuttons_api_key>",
"MAILBUTTONS_API_URL": "https://mailbuttons.com"
}
}
}
}
Environment variables
MAILBUTTONS_API_KEYrequired secret A scoped Mailbuttons MCP token (mb_sandbox_...). Sandbox-by-default; external send requires human promotion.MAILBUTTONS_API_URLBackend base URL. Defaults to https://mailbuttons.com; set for self-hosted or local.
Documentation
From the project's README on GitHub, refreshed weekly. Links open on GitHub.
Mailbuttons MCP server
Governed email for AI agents, over the Model Context Protocol. Give an agent a scoped mailbox where the server enforces the guardrails, not the prompt: sandbox-by-default inboxes, a policy gate on every send, and a tamper-evident audit log. External sending and scope changes are human-approved, never granted by the agent itself.
- Registry:
com.mailbuttons/mcp-server - npm:
@mailbuttons/mcp-server - Platform: mailbuttons.com · agent front door: mbag.ai
Use it
Hosted (recommended) — a streamable-HTTP endpoint served by the platform:
https://mailbuttons.com/api/v1/mcp/rpc
Authorization: Bearer <your Mailbuttons MCP token> # mb_sandbox_... (or mb_prod_...)
Local (stdio) — run the npm package and let your agent launch it:
{
"mcpServers": {
"mailbuttons": {
"command": "npx",
"args": ["-y", "@mailbuttons/mcp-server"],
"env": { "MAILBUTTONS_API_KEY": "mb_sandbox_..." }
}
}
}
Get a scoped token from the dashboard or POST /api/v1/mcp/sandbox-inboxes.
Sandbox tokens can never send externally until a human promotes them.
What the server enforces
- Inbound — a per-mailbox sender policy, fail-closed: mail from strangers bounces by default, so nobody can prompt-inject your agent just by emailing it.
- Outbound — a recipient blocklist the agent can read but not change; a
blocked send returns a normal
{"status":"blocked"}result, not an error. - Caps + audit — per-account send caps and a hash-chained audit log that records refusals too.
- Escalation — sending externally or widening scope is propose-only; a named human approves. The agent cannot approve its own request.
Install as an agent skill
This repo ships a root SKILL.md, so any skills-aware agent can add it:
npx skills add mailbuttons/mcp-server
Docs
- Agent signup (for agents): https://mbag.ai/docs/agent-signup.md
- Trust model: https://mbag.ai/docs/trust-model.md
- OpenAPI: https://mbag.ai/api/openapi.json
- Framework recipes:
references/(Claude Agent SDK, LangChain, plain SDK)
Mailbuttons is a trading name of Code Cutter Limited (UK, no. 08453060). MIT licensed.
Frequently asked questions
What is Mailbuttons (mbag.ai)?
Governed email for AI agents (Mailbuttons / mbag.ai): sandbox inboxes, policy gate, audit log.
How do I install Mailbuttons (mbag.ai)?
It runs as a remote server. In Claude Code: claude mcp add --transport http mailbuttons-mbag-ai 'https://mailbuttons.com/api/v1/mcp/rpc' --header 'Authorization: <Bearer token: a scoped Mailbuttons MCP token, sent as '\''Bearer mb_sandbox_...'\'' (or mb_production_... once promoted). Get one free: sign in with an email code to get an mbk_ API key, then POST https://mailbuttons.com/api/v1/mcp/sandbox-inboxes with it. Guide: https://mailbuttons.com/developers/#mcp>'. For other clients, paste the JSON configuration from this page into their MCP settings.
Does Mailbuttons (mbag.ai) need an API key?
Yes. It expects MAILBUTTONS_API_KEY, Authorization, which you set in its configuration.
Is Mailbuttons (mbag.ai) open source?
Yes. Its code is on GitHub under the MIT license.
Who maintains Mailbuttons (mbag.ai)?
It is published by mailbuttons. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.