# Agent Callback Mailbox (remote · callbacks.inversolabs.us)

Paid replay-safe callback inboxes for asynchronous agent tasks with structured MCP results.

- Trust score: 18/100 (low)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-09

## Components

- remote · `callbacks.inversolabs.us`: 18/100 (this document), [markdown](https://verifymcp.io/servers/us-inversolabs-agent-callback-mailbox/callbacks.md), [page](https://verifymcp.io/servers/us-inversolabs-agent-callback-mailbox/callbacks)

## Channel facts

- Endpoint: `https://callbacks.inversolabs.us/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.54`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-09.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not yet verified: we couldn't confirm whether this endpoint requires it.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 502, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 0/100
  - Transport check failed: declared streamable-http, but the endpoint returned HTTP 502.
- **Schema Quality & AI Usability**: 0/100
  - Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 0/100
  - Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
- **Tool Safety**: 0/100
  - Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
- **Capabilities**: 0/100
  - Capabilities not yet verified: we couldn't read the endpoint's capabilities.

**Unverified: 5 categories.** Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### How do I install the Agent Callback Mailbox MCP server?

Agent Callback Mailbox is a hosted endpoint at https://callbacks.inversolabs.us/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http us-inversolabs-agent-callback-mailbox 'https://callbacks.inversolabs.us/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "us-inversolabs-agent-callback-mailbox": {
      "url": "https://callbacks.inversolabs.us/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "us-inversolabs-agent-callback-mailbox": {
      "type": "http",
      "url": "https://callbacks.inversolabs.us/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.us-inversolabs-agent-callback-mailbox]
url = "https://callbacks.inversolabs.us/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "us-inversolabs-agent-callback-mailbox": {
      "type": "remote",
      "url": "https://callbacks.inversolabs.us/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add us-inversolabs-agent-callback-mailbox --url 'https://callbacks.inversolabs.us/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  us-inversolabs-agent-callback-mailbox:
    url: "https://callbacks.inversolabs.us/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "us-inversolabs-agent-callback-mailbox": {
      "Transport": "http",
      "Url": "https://callbacks.inversolabs.us/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add us-inversolabs-agent-callback-mailbox -t streamable-http -u 'https://callbacks.inversolabs.us/mcp'
```

### Other

```json
{
  "mcpServers": {
    "us-inversolabs-agent-callback-mailbox": {
      "type": "http",
      "url": "https://callbacks.inversolabs.us/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-28 (score 18, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-25 (score 18, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-11 (score 18, −42)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Tool safety: pass → unverified
- [security regression] Stability: 0.50 → unverified
- [security regression] Transport: pass → fail
- [security] Authorization: Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the whole tool list to see what that exposes.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-09-09 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-08 (score 59, +41)

- [security improvement] Injection markers: unverified → pass
- [security improvement] Transport: fail → pass
- [security] Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 1 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
- [functional improvement] Endpoint reachability: not serving MCP → reachable
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.43
- [functional improvement] MCP protocol: unverified → pass

### 2026-09-04 (score 0)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Stability: 0.27 → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Transport: pass → fail
- [security] Authorization: Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the whole tool list to see what that exposes.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-09-02 (score 0)

- [security improvement] Injection markers: unverified → pass
- [security improvement] Transport: fail → pass
- [security] Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 1 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
- [functional improvement] Endpoint reachability: not serving MCP → reachable
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] MCP protocol: unverified → pass

### 2026-09-01 (score 0)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Tool safety: pass → unverified
- [security regression] Stability: 0.17 → unverified
- [security regression] Transport: pass → fail
- [security] Authorization: Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the whole tool list to see what that exposes.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

## MCP tools (1)

### `create_a2a_callback_mailbox` (~153 tokens)

Temporary Authenticated A2A Callback Inbox

Create a temporary private authenticated webhook inbox for asynchronous A2A task completion. Let an expensive reasoning agent suspend instead of spending model calls polling for completion; a lightweight worker can receive and persist the callback, then resume the agent when useful data exists. One payment includes up to 1,000 ordered callback messages, replay-safe deduplication, cursor retrieval, a configurable 1-minute to 24-hour lifetime, and up to 4 MiB storage.

Input parameters:

- `expectedTaskId` (string, required)
- `ingressCredential` (string, required)
- `maxBytes` (integer)
- `maxEvents` (integer)
- `retrievalCredential` (string, required)
- `ttlMinutes` (integer)

Output parameters:

- `authentication_scheme` (string)
- `callback_url` (string)
- `expires_at` (string)
- `mailbox_id` (string)
- `max_bytes` (integer)
- `max_events` (integer)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/us-inversolabs-agent-callback-mailbox/callbacks#diagnostics

## Score history

- 2026-10-09: 18
- 2026-10-04: 18
- 2026-10-03: 18
- 2026-10-02: 18
- 2026-10-01: 18
- 2026-09-30: 18
- 2026-09-29: 18
- 2026-09-28: 18
- 2026-09-27: 18
- 2026-09-26: 18
- 2026-09-25: 18
- 2026-09-24: 18
- 2026-09-23: 18
- 2026-09-22: 18
- 2026-09-21: 18
- 2026-09-20: 18
- 2026-09-19: 18
- 2026-09-18: 18
- 2026-09-17: 18
- 2026-09-16: 18
- 2026-09-15: 18
- 2026-09-14: 18
- 2026-09-13: 18
- 2026-09-12: 18
- 2026-09-11: 18
- 2026-09-10: 60
- 2026-09-09: 60
- 2026-09-08: 59
- 2026-09-07: 18
- 2026-09-06: 18

## Common questions

### What is the Agent Callback Mailbox MCP server?

Agent Callback Mailbox is an MCP server listed in the public MCP registry as us.inversolabs/agent-callback-mailbox. Paid replay-safe callback inboxes for asynchronous agent tasks with structured MCP results. This page covers its hosted endpoint (https://callbacks.inversolabs.us/mcp).

### Is the Agent Callback Mailbox MCP server safe to use?

Agent Callback Mailbox scores 18 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Agent Callback Mailbox MCP server expose?

Agent Callback Mailbox exposes 1 tool: create_a2a_callback_mailbox. Their descriptions and schemas cost roughly 153 tokens of context every time the server is loaded.

### Does the Agent Callback Mailbox MCP server require authentication?

Its publisher declares no required credentials for Agent Callback Mailbox. We have not been able to confirm that against the live endpoint, and a server can require authorisation without declaring it here.

### Is the Agent Callback Mailbox MCP server still maintained?

Agent Callback Mailbox is still listed as active in the MCP registry. We last reached this channel on 9 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://callbacks.inversolabs.us/mcp
- Changelog RSS feed: https://verifymcp.io/servers/us-inversolabs-agent-callback-mailbox/callbacks.xml
- Changelog JSON feed: https://verifymcp.io/servers/us-inversolabs-agent-callback-mailbox/callbacks.json
- HTML version of this page: https://verifymcp.io/servers/us-inversolabs-agent-callback-mailbox/callbacks