# AHOOK (remote · ahook.app)

Webhooks designed for agents. Create inboxes, wait for events, list and extract them.

- Trust score: 67/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `ahook.app`: 67/100 (this document), [markdown](https://verifymcp.io/servers/app-ahook-ahook/ahook.md), [page](https://verifymcp.io/servers/app-ahook-ahook/ahook)

## Channel facts

- Endpoint: `https://ahook.app/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## 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 2026-11-21.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (delete_inbox).
  - HTTPS check failed: the endpoint is reachable over plaintext HTTP.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 72/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1334 tokens (~121/item across 11 items; 11 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 53/100
  - Stability observed for 16 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the AHOOK MCP server?

AHOOK is a hosted endpoint at https://ahook.app/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 app-ahook-ahook 'https://ahook.app/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "app-ahook-ahook": {
      "url": "https://ahook.app/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "app-ahook-ahook": {
      "type": "http",
      "url": "https://ahook.app/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.app-ahook-ahook]
url = "https://ahook.app/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "app-ahook-ahook": {
      "type": "remote",
      "url": "https://ahook.app/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add app-ahook-ahook --url 'https://ahook.app/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  app-ahook-ahook:
    url: "https://ahook.app/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "app-ahook-ahook": {
      "Transport": "http",
      "Url": "https://ahook.app/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add app-ahook-ahook -t streamable-http -u 'https://ahook.app/mcp'
```

### Other

```json
{
  "mcpServers": {
    "app-ahook-ahook": {
      "type": "http",
      "url": "https://ahook.app/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.

### 2026-11-21 (score 67, 0)

- [functional regression] Schema quality: pass → fail
- [functional] New tool “submit_feedback”

### 2026-11-20 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 66, +1)

- [security] New tool “delete_event”, which the server declares destructive
- [security] Tool “delete_inbox” rewrote its description, which is the text the model reads
- [functional improvement] Schema quality: fail → pass
- [functional] New tool “get_inbox”
- [functional] New tool “list_inboxes”

### 2026-11-17 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-15 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-13 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-11 (score 62, 0)

- [functional regression] Schema quality: pass → fail
- [functional] New tool “search”

### 2026-11-10 (score 62, +1)

- [security] The server rewrote its instructions, which are the text every model session reads

## MCP tools (11)

### `create_inbox` (~147 tokens)

Create a webhook inbox. Returns its ingest URL and a read token (shown once). The same slug is the inbox email address <slug>@ahook.app. Optional slug: a branded username for the inbox (3-63 lowercase letters, digits, and hyphens) — any account may pick one, including anonymous-free via MCP; the inbox never expires, so the slug is permanent. Reserved names are rejected (invalid_slug) and a taken name returns slug_taken.

Input parameters:

- `slug` (string): Optional username slug for the inbox (e.g. vintagefinds). Any account may pick one, including anonymous-free via MCP; the inbox never expires, so the slug is permanent.

### `wait_for_event` (~127 tokens)

Wait for the next event in an inbox after a cursor, up to 30s. Auth: Authorization Bearer read token header.

Input parameters:

- `after` (integer): Only return the first event with an id greater than this cursor (0 for the first event).
- `body_contains` (string): Only return an event whose body contains this text.
- `inbox_id` (string, required): The inbox id returned when the inbox was created (private; the slug in the ingest URL is the public part).
- `timeout_ms` (integer): How long to wait in milliseconds (max 30000).

### `list_events` (~83 tokens)

List events in an inbox. Auth: Authorization Bearer read token header.

Input parameters:

- `after` (integer): Only list events with an id greater than this cursor.
- `inbox_id` (string, required): The inbox id returned when the inbox was created (private; the slug in the ingest URL is the public part).
- `limit` (integer): Maximum number of events to return.

### `get_event` (~67 tokens)

Get one event by id. Auth: Authorization Bearer read token header.

Input parameters:

- `event_id` (integer, required): The numeric id of the event.
- `inbox_id` (string, required): The inbox id returned when the inbox was created (private; the slug in the ingest URL is the public part).

### `extract_field` (~93 tokens)

Pull a JSON path out of an event body. Auth: Authorization Bearer read token header.

Input parameters:

- `event_id` (integer, required): The numeric id of the event.
- `inbox_id` (string, required): The inbox id returned when the inbox was created (private; the slug in the ingest URL is the public part).
- `json_path` (string, required): Dot-separated path into the event JSON body, e.g. user.email.

### `delete_inbox` (~99 tokens)

Delete an inbox and its events. Auth: Authorization Bearer read token header. Irreversible: under a PAP session this needs a user approval first (Operations v3) - the first call returns the operation to approve; retry with the approval in _meta[personalagentprotocol.org/approval].

Input parameters:

- `inbox_id` (string, required): The inbox id returned when the inbox was created (private; the slug in the ingest URL is the public part).

### `get_inbox` (~53 tokens)

Get one inbox: its slug, ingest URL, plan, status, and event count. Auth: Authorization Bearer read token header.

Input parameters:

- `inbox_id` (string, required): The inbox id returned when the inbox was created.

### `list_inboxes` (~29 tokens)

List the inboxes linked to your AHOOK account. Auth: Authorization Bearer account key header.

### `delete_event` (~65 tokens)

Delete one event from an inbox (per-event purge). Auth: Authorization Bearer read token header. Archived (cold-storage) events cannot be purged this way.

Input parameters:

- `event_id` (integer, required): The event id to delete.
- `inbox_id` (string, required): The inbox id.

### `search` (~257 tokens)

Search the public API index (AHOOK Search, 14,000+ callable APIs and MCP servers). Ranks for whether an agent can actually use a result: BM25 text relevance plus readiness (machine interface, declared auth, liveness, llms.txt, ownership, example call), freshness, authority, and completeness. Every result carries its score_breakdown. Auth: Authorization Bearer ahk_ account key header (create one with POST /api/v1/accounts). One search = 1 metered read (meter search_queries, included in the $1 base, no per-search charge in v1). Rate limit: free 10/min, paid 60/min.

Input parameters:

- `category` (string): Exact category match, e.g. tts, coding, ai-models, payments.
- `free_commercial` (boolean): Only results whose free tier states commercial use.
- `limit` (number): Max results, 1..50, default 10.
- `max_token_cost` (number): Only results whose token_cost.input_per_1m fits.
- `max_unit_cost` (number): Only results whose unit_cost.amount_min fits.
- `query` (string, required): Search terms. Empty = browse mode: highest score first.

### `submit_feedback` (~256 tokens)

File feedback for the AHOOK team as a support ticket: a feature request, a bug, something confusing, or anything else. A human reviews every filing; nothing is auto-built from it. Limited to 6 filings per day. Returns the ticket id and a public status URL.

Input parameters:

- `callback_url` (string): An https URL to notify when the feedback is reviewed or resolved. Must be a public https URL; private or internal URLs are rejected (platform-wide internal-URL block).
- `error` (string): The error text or message the agent hit, if the feedback is about an error.
- `kind` (string): The kind of feedback. Defaults to feature_request.
- `property` (string): The property slug (for example "main-landing") or group id. Under a PAP session it defaults to the session's property and cannot be overridden. With a bare account key it is required.
- `session_id` (string): The agent's session id, if it has one.
- `text` (string, required): The feedback, bug report, or feature request, in your own words. Required. Maximum 2000 characters.
- `tool_name` (string): The MCP tool the feedback is about, if any.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/app-ahook-ahook/ahook#diagnostics

## Score history

- 2026-11-21: 67
- 2026-11-20: 67
- 2026-11-19: 66
- 2026-11-18: 66
- 2026-11-17: 65
- 2026-11-16: 64
- 2026-11-15: 64
- 2026-11-14: 63
- 2026-11-13: 63
- 2026-11-12: 62
- 2026-11-11: 62
- 2026-11-10: 62
- 2026-11-09: 61
- 2026-11-08: 61
- 2026-11-07: 60
- 2026-11-06: 60
- 2026-11-05: 59

## Common questions

### What is the AHOOK MCP server?

AHOOK is an MCP server listed in the public MCP registry as app.ahook/ahook. Webhooks designed for agents. Create inboxes, wait for events, list and extract them. This page covers its hosted endpoint (https://ahook.app/mcp).

### Is the AHOOK MCP server safe to use?

AHOOK scores 67 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 AHOOK MCP server expose?

AHOOK exposes 11 tools: create_inbox, wait_for_event, list_events, get_event, extract_field, and 6 more. Their descriptions and schemas cost roughly 1,276 tokens of context every time the server is loaded.

### Does the AHOOK MCP server require authentication?

No. We connected to AHOOK without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the AHOOK MCP server still maintained?

AHOOK is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the AHOOK MCP server?

VerifyMCP ran 13 checks on AHOOK, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://ahook.app/mcp
- Repository: https://github.com/ahook-app/ahook
- Website: https://ahook.app/
- Changelog RSS feed: https://verifymcp.io/servers/app-ahook-ahook/ahook.xml
- Changelog JSON feed: https://verifymcp.io/servers/app-ahook-ahook/ahook/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/app-ahook-ahook/ahook.json
- HTML version of this page: https://verifymcp.io/servers/app-ahook-ahook/ahook
