mailbox.bot publishes an Agentic Resource Discovery manifest at /.well-known/ai-catalog.json, declaring what an AI agent can call on this domain. Everything below is read from that file. First seen by our crawler on 31 August 2026.
| Declared resource | Type |
|---|---|
| mailbox.bot A2A Agentanswers in 249ms A2A agent card for delegating task-based postal workflows: outbound mail, inbound context, linked replies, managed-address reservations, webhooks, and standing instructions. endpoint: https://mailbox.bot/.well-known/agent-card.jsonidentifier: urn:ai:mailbox.bot:agent:a2apostal-mail a2a agent-card certified-mail task-delegation inbound-context webhooks provision-address | application/a2a-agent-card+json |
| mailbox.bot Multi-Protocol Agent Cardanswers in 137msv1.1.2 Mailbox.bot discovery document covering REST, MCP, OpenClaw, webhooks, live outbound mail, live existing-address inbound context, account-enabled custody at already-assigned PMBs, new managed address reservations (Not live yet · Launch ETA: mid/late Septemb... endpoint: https://mailbox.bot/.well-known/agent.jsonidentifier: urn:ai:mailbox.bot:agent:openclawpublished to be found for: discover mailbox.bot agent protocols · find the mailbox.bot MCP and REST endpoints · learn mailbox.bot onboarding and pricing metadata · find framework guides for agent postal mail postal-mail agent-discovery openclaw mcp openapi webhooks protocol discovery capability discovery | application/vnd.openclaw.agent+json |
| mailbox.bot MCP Serveranswers in 415msv1.1.2 MCP server with 19 tools for AI agents to send live outbound postal mail, use live forwarded digital/OCR inbound context from existing addresses, and manage postal threads. New mailbox.bot-issued physical receiving, street, and package addresses: Not live y... endpoint: https://mailbox.bot/.well-known/mcp/server-card.jsonidentifier: urn:ai:mailbox.bot:server:mcppublished to be found for: send a certified letter from an AI agent · mail a PDF with dry-run pricing and approval · read forwarded mail scans and send a physical reply · track outbound postal mail status from code postal-mail mcp certified-mail outbound-mail inbound-context postal-threads webhooks ai-agents | application/mcp-server+json |
| mailbox.bot REST APIanswers in 520msvv1 OpenAPI 3.1 description for mailbox.bot's REST API: send live postal mail, price dry runs, use sandbox lifecycle simulation, read live inbound context forwarded from existing addresses, manage postal threads, configure webhooks, and administer agent credent... endpoint: https://mailbox.bot/openapi.jsonidentifier: urn:ai:mailbox.bot:api:rest-v1published to be found for: integrate a postal mail API with webhooks · generate code to send certified mail from my app · create sandbox test mail and advance its lifecycle · fetch inbound document context for a postal reply postal-mail openapi rest-api certified-mail batch-mail sandbox physical-inbound webhooks | application/vnd.oai.openapi+json |
| mailbox.bot Skillanswers in 301msv5.1.7 Skill instructions for AI assistants using mailbox.bot: when to send outbound postal mail, how to install MCP, how to handle human approval, and how to distinguish live forwarded digital/OCR context, managed address reservations (Not live yet · Launch ETA: ... endpoint: https://raw.githubusercontent.com/arbengine/mailbox-bot-skill/main/SKILL.mdidentifier: urn:ai:mailbox.bot:skill:mailbox-botpublished to be found for: how should my agent use mailbox.bot to send mail · install the mailbox.bot MCP server · when should an AI workflow use certified mail · how do agents handle mailbox.bot signup and approval postal-mail skill mcp agent-instructions certified-mail inbound-context human-approval agent guidance | application/ai-skill |
https://mailbox.bot/.well-known/ai-catalog.json, this publisher's own file. Identifiers are reproduced exactly as published.
Note: this is the pre-v0.91 path. The specification renamed the manifest to /.well-known/ard.json, and most of the ecosystem still serves the older name.
Of the resources listed, 5 have been probed for reachability.
"Answers" and "no response" describe only whether an endpoint replied when last probed:
services go down and come back, and an entry is demoted rather than removed. None of this
is a trust, quality or safety rating.
https://neuronto.com/search, or connect an agent to https://neuronto.com/mcp.
If this is your domain, the free console shows what a registry
sees when it reads your manifest.