# Postal

> Use this tool when you need to enable asynchronous communication between AI agents, allowing them to exchange messages and coordinate tasks through a persistent database queue. It solves problems of inter-agent communication, information sharing, and task handoffs in multi-agent workflows. The Postal tool provides a simple interface with send_to_agent and check_mail functions, accessible through unique HTTP endpoints for each agent.

Canonical page: https://skillsregistry.net/skills/postal  
JSON: https://api.skillsregistry.net/v1/skills/postal

## Description

This MCP server implementation creates a mailbox system enabling two AI agents to communicate asynchronously through message passing. Built by Tim Kellogg using FastAPI and SQLite, it provides send_to_agent and check_mail tools that allow agents to exchange messages via a persistent database queue. The server supports multi-agent workflows where agents need to coordinate tasks, share information, or hand off work to each other, with each agent accessing their own mailbox through unique HTTP endpoints.

## Trust

- **Trust score (0–1):** 0.99
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/postal)
- **Repository:** <https://github.com/tkellogg/postal-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "postal"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/postal` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/postal/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt