mailbox-mcp
Official mailbox.bot MCP server for AI agents. Send letters, certified mail, postcards, and receive scanned inbound physical mail with sandbox keys, approval controls, tracking, and webhooks.
README
mailbox.bot MCP server
Official Model Context Protocol (MCP) server manifest for mailbox.bot — a physical postal mail API for AI agents. Send certified mail, letters, notices, and postcards — we print, stamp, and mail them with photos scanned and tracked. Turn your business mailbox address, PO Box, home office address, or virtual mailbox into inbound agentic context. Get a new postal receiving mailbox address is in private beta.
Send letters, certified mail, and packages from your agent. Sandbox keys for zero-charge testing on the same production endpoints.
- Website: https://mailbox.bot
- Install: https://mailbox.bot/mcp-install
- Docs: https://mailbox.bot/api-docs
- Registry:
bot.mailbox/mailbox(DNS-verified onmailbox.bot)
What this repo is
This repository holds the public server.json manifest published to the official MCP Registry. The server itself is hosted at https://mailbox.bot/api/mcp (streamable HTTP transport) — there is no code to install.
If you're trying to use the server, go to mailbox.bot/mcp-install for client-specific setup (Claude Code, Claude Desktop, Cursor, etc.).
Verifying authenticity
The namespace bot.mailbox/* is reserved via DNS proof on the apex domain mailbox.bot. Only the domain owner can publish servers under this namespace to the MCP Registry. If you see another server claiming to be mailbox.bot under a different namespace, it is not official.
The canonical manifest lives in this repo and is mirrored to the registry — both should match exactly.
Capabilities
- Outbound mail — send first-class letters, certified postal mail, and other USPS / FedEx / UPS classes from a PDF or a few common document formats.
- Inbound mail — receive, scan, forward, and shred physical mail at a US address in private beta.
- Sandbox mode —
sk_agent_test_keys exercise the full lifecycle (fulfillment photos, tracking, dispatch) with zero charge. - Cost controls —
dry_runcost preview,X-Max-Cost-Centscap, per-key daily piece limits, structured retryable errors. - Webhooks — signed delivery events with full payload inspection via REST.
Full tool list and schemas: see the docs and the OpenAPI spec at mailbox.bot/openapi.json.
License
MIT — covers this manifest and any examples added to this repo. The mailbox.bot service itself is operated under the mailbox.bot terms.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.