# Askline (remote · askline.ai)

Askline shows what ChatGPT says about a brand, then the SEO that feeds it.

- Trust score: 37/100 (low)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `askline.ai`: 37/100 (this document), [markdown](https://verifymcp.io/servers/ai-askline-askline/askline.md), [page](https://verifymcp.io/servers/ai-askline-askline/askline)

## Channel facts

- Endpoint: `https://askline.ai/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 2026-09-20.

- **Endpoint Security**: 92/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - The endpoint enforces authorisation, advertised via RFC 9728 protected-resource metadata.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server supports Client ID Metadata Documents, the current MCP client-registration mechanism.
- **Transport & Reachability**: 0/100
  - Transport blocked by authentication: the endpoint requires auth we don't have to verify streamable-http.
- **Schema Quality & AI Usability**: 0/100
  - Schema blocked by authentication: the endpoint requires auth we don't have to read it.
- **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 blocked by authentication: the endpoint requires auth we don't have to read its tools.
- **Tool Safety**: 0/100
  - Tool safety blocked by authentication: the endpoint requires auth we don't have to read its tools.
- **Capabilities**: 0/100
  - Capabilities blocked by authentication: the endpoint requires auth we don't have to read them.

**Unverified: 6 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 Askline MCP server?

Askline is a hosted endpoint at https://askline.ai/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 ai-askline-askline 'https://askline.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-askline-askline": {
      "url": "https://askline.ai/mcp"
    }
  }
}
```

### VS Code

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

### Codex

```toml
[mcp_servers.ai-askline-askline]
url = "https://askline.ai/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add ai-askline-askline --url 'https://askline.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-askline-askline:
    url: "https://askline.ai/mcp"
```

### Netclaw

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

### Vellum

```bash
assistant mcp add ai-askline-askline -t streamable-http -u 'https://askline.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-askline-askline": {
      "type": "http",
      "url": "https://askline.ai/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.

### 2026-08-30 (score 37, −35)

- [security regression] Endpoint reachability: reachable → behind authorisation
- [security regression] Tool safety: pass → unverified
- [security regression] Transport: pass → unverified
- [security regression] Stability: 0.03 → unverified
- [security improvement] Authorization: fail → pass
- [security] First check of Authorization: pass
- [functional regression] Capabilities: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified

### 2026-08-29 (score 72, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-08-28 (score 72)

First indexed and scored.

## MCP tools (22)

### `keyword_research` (~69 tokens)

Keyword research

Find related keywords with monthly search volume and keyword difficulty for a seed term. Uses the saved Project market when location is omitted. Costs 1 lookup.

Input parameters:

- `keyword` (string, required)
- `language_code` (string)
- `limit` (number)
- `location_code` (number)

Output parameters:

- `language_code` (string)
- `location_code` (number)
- `location_label` (string)
- `project_domain` (string|null)
- `remaining_lookups` (number|null)
- `rows` (array)
- `seed` (string)
- `source` (string)

### `keyword_difficulty` (~69 tokens)

Score how hard it is to rank in the top 10 for one or more keywords (0–100). Uses the saved Project market when location is omitted. Costs 1 lookup.

Input parameters:

- `keywords` (array, required)
- `language_code` (string)
- `location_code` (number)

### `serp_overview` (~63 tokens)

Live Google organic SERP: ranking URLs, titles, and SERP features. Uses the saved Project market when location is omitted. Costs 1 lookup.

Input parameters:

- `keyword` (string, required)
- `language_code` (string)
- `location_code` (number)

### `domain_overview` (~63 tokens)

Organic traffic, ranking keywords, and domain rank for a host. Uses the saved Project domain and market when those args are omitted. Costs 1 lookup.

Input parameters:

- `language_code` (string)
- `location_code` (number)
- `target` (string)

### `ranked_keywords` (~66 tokens)

Keywords a domain already ranks for, with position and volume. Uses the saved Project when target or location is omitted. Costs 1 lookup.

Input parameters:

- `language_code` (string)
- `limit` (number)
- `location_code` (number)
- `target` (string)

### `competitor_keywords` (~67 tokens)

Keywords competitors rank for that the target does not, plus overlap. Uses the saved Project when target or location is omitted. Costs 1 lookup.

Input parameters:

- `competitor` (string)
- `language_code` (string)
- `location_code` (number)
- `target` (string)

### `backlink_overview` (~39 tokens)

Backlink count, referring domains, rank, and spam score (2 lookups). Costs 2 lookups.

Input parameters:

- `target` (string)

### `referring_domains` (~41 tokens)

Domains linking to the target, with rank (2 lookups). Costs 2 lookups.

Input parameters:

- `limit` (number)
- `target` (string)

### `link_gap` (~44 tokens)

Referring domains that link to competitors but not the target (2 lookups). Costs 2 lookups.

Input parameters:

- `competitors` (array, required)
- `target` (string)

### `site_audit` (~63 tokens)

On-page audit of one URL via instant pages. Stores the last run so a re-audit reports what changed (1 lookup). Costs 1 lookup.

Input parameters:

- `max_pages` (number): Ignored. Instant pages audits one URL.
- `target` (string)

### `chatgpt_answer` (~100 tokens)

Live ChatGPT or Gemini answer for a prompt: the text, recommended brands, and cited URLs. Uses the saved Project market when location is omitted. Takes up to 2 minutes (1 lookup). Costs 1 lookup.

Input parameters:

- `keyword` (string, required): Prompt or question, e.g. best project management software
- `language_code` (string)
- `location_code` (number)
- `platform` (string): Default chat_gpt

### `ai_search_volume` (~67 tokens)

How often people ask ChatGPT-class tools about these keywords. Uses the saved Project market when location is omitted (1 lookup). Costs 1 lookup.

Input parameters:

- `keywords` (array, required): Up to 20 keywords
- `language_code` (string)
- `location_code` (number)

### `llm_citations` (~115 tokens)

Pages and domains ChatGPT and AI Overviews quote for a topic or competitor. Pass a domain, a keyword, or both. ChatGPT mention data is US/English only (10 lookups). Costs 10 lookups.

Input parameters:

- `keyword` (string): Topic AI is answering, e.g. seo tools
- `language_code` (string)
- `location_code` (number)
- `platform` (string): Default both platforms
- `target` (string): Your domain, e.g. ahrefs.com

### `ai_mentions` (~70 tokens)

How often Google AI Overviews and ChatGPT mention a brand or domain (10 lookups). Costs 10 lookups.

Input parameters:

- `keyword` (string)
- `language_code` (string)
- `location_code` (number)
- `platform` (string)
- `target` (string)

### `ai_share_of_voice` (~65 tokens)

Share of AI recommendations versus named competitors (10 lookups). Costs 10 lookups.

Input parameters:

- `competitors` (array)
- `keyword` (string)
- `language_code` (string)
- `location_code` (number)
- `target` (string)

### `gsc_performance` (~32 tokens)

Google Search Console totals: clicks, impressions, average position. 0 credits. Costs 0 lookups.

### `gsc_queries` (~34 tokens)

Search Console queries for the connected property. 0 credits. Costs 0 lookups.

Input parameters:

- `limit` (number)

### `gsc_pages` (~34 tokens)

Search Console pages for the connected property. 0 credits. Costs 0 lookups.

Input parameters:

- `limit` (number)

### `research_memory` (~50 tokens)

Read or write project notes so research compounds across chats. 0 credits. Costs 0 lookups.

Input parameters:

- `action` (string, required)
- `key` (string)
- `value` (string)

### `pin_finding` (~43 tokens)

Pin a finding to the account and SEO Board. 0 credits. Costs 0 lookups.

Input parameters:

- `body` (string, required)
- `title` (string, required)

### `get_project` (~35 tokens)

Return the saved Project (primary domain and market) for this MCP user. Free — not a lookup. Costs 0 lookups.

### `set_project` (~91 tokens)

Save this user's Project: primary domain and market (country + language, e.g. in-en or India English). Later keyword, SERP, and competitor tools use it when domain or locale are omitted. Free — not a lookup. Costs 0 lookups.

Input parameters:

- `domain` (string, required)
- `language_code` (string)
- `location_code` (number)
- `market` (string)

## Diagnostics

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

## Score history

- 2026-09-20: 37
- 2026-09-19: 37
- 2026-09-18: 37
- 2026-09-17: 37
- 2026-09-16: 37
- 2026-09-15: 37
- 2026-09-14: 37
- 2026-09-13: 37
- 2026-09-12: 37
- 2026-09-11: 37
- 2026-09-10: 37
- 2026-09-09: 37
- 2026-09-08: 37
- 2026-09-07: 37
- 2026-09-06: 37
- 2026-09-05: 37
- 2026-09-04: 37
- 2026-09-03: 37
- 2026-09-02: 37
- 2026-09-01: 37
- 2026-08-31: 37
- 2026-08-30: 37
- 2026-08-29: 72
- 2026-08-28: 72

## Common questions

### What is the Askline MCP server?

Askline is an MCP server listed in the public MCP registry as ai.askline/askline. Askline shows what ChatGPT says about a brand, then the SEO that feeds it. This page covers its hosted endpoint (https://askline.ai/mcp).

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

Askline scores 37 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 Askline MCP server expose?

Askline exposes 22 tools: keyword_research, keyword_difficulty, serp_overview, domain_overview, ranked_keywords, and 17 more. Their descriptions and schemas cost roughly 1,320 tokens of context every time the server is loaded.

### Does the Askline MCP server require authentication?

Yes. Askline asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Askline MCP server still maintained?

Askline is still listed as active in the MCP registry. We last reached this channel on 20 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://askline.ai/mcp
- Website: https://askline.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-askline-askline/askline.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-askline-askline/askline.json
- HTML version of this page: https://verifymcp.io/servers/ai-askline-askline/askline