# Engagemii Citation Watch (remote · api.engagemii.com)

Brands ChatGPT names for real buyer questions, updated every 30 minutes, with AI visibility scores.

- Trust score: 64/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-25

## Components

- remote · `api.engagemii.com`: 64/100 (this document), [markdown](https://verifymcp.io/servers/com-engagemii-citation-watch/api-mcp.md), [page](https://verifymcp.io/servers/com-engagemii-citation-watch/api-mcp)

## Channel facts

- Endpoint: `https://api.engagemii.com/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## 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 2026-09-25.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 13 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 71/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1960 tokens (~150/item across 13 items; 13 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 7/100
  - Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 87/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 60% 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.
  - We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 40/100
  - Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28.

## Install

### How do I install the Engagemii Citation Watch MCP server?

Engagemii Citation Watch is a hosted endpoint at https://api.engagemii.com/api/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 com-engagemii-citation-watch 'https://api.engagemii.com/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-engagemii-citation-watch": {
      "url": "https://api.engagemii.com/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-engagemii-citation-watch": {
      "type": "http",
      "url": "https://api.engagemii.com/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-engagemii-citation-watch]
url = "https://api.engagemii.com/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-engagemii-citation-watch": {
      "type": "remote",
      "url": "https://api.engagemii.com/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-engagemii-citation-watch --url 'https://api.engagemii.com/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-engagemii-citation-watch:
    url: "https://api.engagemii.com/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-engagemii-citation-watch": {
      "Transport": "http",
      "Url": "https://api.engagemii.com/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-engagemii-citation-watch -t streamable-http -u 'https://api.engagemii.com/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-engagemii-citation-watch": {
      "type": "http",
      "url": "https://api.engagemii.com/api/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.

### 2026-09-25 (score 64, +1)

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

### 2026-09-24 (score 63, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-09-23 (score 63)

First indexed and scored.

## MCP tools (13)

### `aeo_score` (~87 tokens)

Get the Engagemii AEO score (0-10) for any company domain, with the six on-page sub-scores, seven off-page authority signals, and the llms.txt audit verdict. Drawn from Engagemii's 40 million+ scored-company dataset. Free, no auth.

Input parameters:

- `domain` (string, required): Company domain or URL, e.g. example.com

### `aeo_audit` (~114 tokens)

Run a LIVE AEO audit of a site right now: fresh fetch of the homepage, robots.txt, sitemap, llms.txt, and about page, scored on the six on-page categories with concrete recommendations. Use this to verify fixes immediately after applying them; aeo_score returns the stored dataset score, which updates when Engagemii next crawls the site. Free, no auth, up to 5 live audits per hour.

Input parameters:

- `domain` (string, required): Company domain or URL, e.g. example.com

### `brand_profile` (~47 tokens)

Full public profile for a scored company: score breakdown, category, geography, detected platform, social profiles, AI-crawler visit counts. Free, no auth.

Input parameters:

- `domain` (string, required)

### `dataset_sample` (~39 tokens)

15 random live rows from the Engagemii dataset in exactly the shape a purchased file delivers (same columns, same cleaning). Free, no auth.

### `citation_watch` (~152 tokens)

What ChatGPT is recommending right now. Every 30 minutes Engagemii puts a real, non-branded buyer question to ChatGPT with live web search and records which brands it names, alongside each brand's standing AI visibility score (computed before the question was asked). Returns the last 48 hours. Free, no auth. Use this to answer questions like 'which brands does AI recommend in category X' or 'is an AI visibility score related to being recommended'.

Input parameters:

- `category` (string): Optional filter, e.g. Legal, Finance & Insurance, Fashion & Apparel. Case-insensitive substring match.
- `limit` (number): How many checks to return, 1 to 50. Default 20.

### `ai_readstream` (~125 tokens)

Which AI engines are reading the business web right now. Server-side, IP-verified crawler logs across one of the largest networks of business pages online. Returns per-engine reads over the last ten minutes, the last 24 hours and all time, plus a daily series. Free, no auth. Use this to answer 'which AI crawler is most active', 'how much is Claude reading compared to GPTBot', or 'is AI crawling going up'.

Input parameters:

- `days` (number): How many days of the daily series to return, 0 to 30. Default 7.

### `free_kit` (~206 tokens)

Request the FREE Customized Fix Kit for a domain. There is one kit and it is free: eight fix files written from the site's ACTUAL content (Organization and FAQ JSON-LD, meta description, llms.txt, robots patch, Wikidata guide, Google Business checklist, README) plus a full PDF audit. Flow: pass the owner's email; Engagemii emails a verification link; after the owner clicks it the kit is built and the download link is emailed automatically. Kits are queued, so delivery is by email rather than in-chat. One kit per domain; repeat requests resend the stored kit.

Input parameters:

- `domain` (string, required): The site, e.g. example.com
- `email` (string, required): The site owner's email (the verification link and the kit go there)
- `owner_confirmed` (boolean, required): Confirm with the user that this is their own brand. Agencies working on client sites should use the data portal (engagemii.com/aeo/data) instead.

### `connect_tracker` (~230 tokens)

Set up free Engagemii AI-crawler monitoring for a site, entirely from here. It provisions the owner's free account and tracker key and returns a small install snippet (Node/Express, Next.js, PHP, or Cloudflare Worker) with the key already in it. Install the one that matches the site's stack (if you are working in the site's own code, just add the file yourself) and AI-bot visits start reporting; the owner watches them per bot, per day at the dashboard link. Requires the owner's email. Before connecting, tell the owner: Engagemii is free because it licenses the AI-crawler activity data the tracker collects, in aggregated form and, unless the owner opts out in portal settings, identified by their domain. The tracker records bot visits only, never their human visitors. Only connect if the owner is fine with that.

Input parameters:

- `domain` (string, required): The site, e.g. example.com
- `email` (string, required): The site owner's email (required)
- `platform` (string): The site's stack, if known. Omit to get all four snippets.

### `search_companies` (~111 tokens)

Query the scored dataset with filters (industries, states, score range, scope us|all). Returns up to 100 light rows. Requires an Engagemii data API key.

Input parameters:

- `industries` (array): Business categories, e.g. Technology, Healthcare
- `limit` (number): max 100
- `scope` (string): us = verified US companies; all = worldwide
- `scoreMax` (number)
- `scoreMin` (number)
- `states` (array)

### `data_signup` (~167 tokens)

Create a free Engagemii data account. We email a verification link to the address; the account's API key (edk_...) stays inactive until the user clicks it, then the key appears in the portal and unlocks search_companies and data_records. Requires the user's email, a password of their choosing (8+ characters), their company name, and their EXPLICIT confirmation that they accept the data license at https://engagemii.com/aeo/data/license. Only set license_accepted to true if the user actually said yes.

Input parameters:

- `company_name` (string, required)
- `email` (string, required)
- `license_accepted` (boolean, required): true ONLY if the user explicitly accepted the license
- `password` (string, required): 8+ characters, chosen by the user

### `data_records` (~191 tokens)

Pull full licensed records from the Engagemii dataset (all columns, fingerprinted, the same shape a purchased file delivers). METERED: every record returned is deducted from the account's purchased API quota, so keep limits small in conversation (default 25, max 100 here). For bulk pulls use the raw API: POST https://api.engagemii.com/api/v1/data/records with the same key and filters (up to 10,000 per call). Requires an Engagemii data API key. To browse without spending quota, use search_companies or dataset_sample instead.

Input parameters:

- `industries` (array)
- `limit` (number): records to draw (each costs 1 quota). Default 25, max 100 in-chat.
- `scope` (string)
- `scoreMax` (number)
- `scoreMin` (number)
- `states` (array)

### `kit_checkout` (~75 tokens)

RETIRED: the Customized Fix Kit is now free, so there is nothing to buy. Call free_kit with the owner's email instead; the kit arrives by email after a one-click verification. This tool remains only so older conversations get a helpful answer.

Input parameters:

- `domain` (string): The site, e.g. example.com

### `kit_download` (~74 tokens)

After a paid kit_checkout, receive all eight Customized Fix Kit files plus the badge embed as plain text so an agent can apply them directly to the codebase and re-run aeo_audit to verify the improvement. Requires the Stripe session id (cs_...) from the checkout success URL.

Input parameters:

- `session_id` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-engagemii-citation-watch/api-mcp#diagnostics

## Score history

- 2026-09-25: 64
- 2026-09-24: 63
- 2026-09-23: 63

## Common questions

### What is the Engagemii Citation Watch MCP server?

Engagemii Citation Watch is an MCP server listed in the public MCP registry as com.engagemii/citation-watch. Brands ChatGPT names for real buyer questions, updated every 30 minutes, with AI visibility scores. This page covers its hosted endpoint (https://api.engagemii.com/api/mcp).

### Is the Engagemii Citation Watch MCP server safe to use?

Engagemii Citation Watch scores 64 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 Engagemii Citation Watch MCP server expose?

Engagemii Citation Watch exposes 13 tools: aeo_score, aeo_audit, brand_profile, dataset_sample, citation_watch, and 8 more. Their descriptions and schemas cost roughly 1,618 tokens of context every time the server is loaded.

### Does the Engagemii Citation Watch MCP server require authentication?

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

### Is the Engagemii Citation Watch MCP server still maintained?

Engagemii Citation Watch is still listed as active in the MCP registry. We last reached this channel on 25 September 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://api.engagemii.com/api/mcp
- Website: https://engagemii.com/live
- Changelog RSS feed: https://verifymcp.io/servers/com-engagemii-citation-watch/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-engagemii-citation-watch/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-engagemii-citation-watch/api-mcp