# SEO Data MCP (SteadyScrape) (remote · mcp.steadyscrape.dev)

Keyword volume, live SERP ranks, domain traffic, ranked keywords, backlinks, Google Trends, YouTube.

- Trust score: 65/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `mcp.steadyscrape.dev`: 65/100 (this document), [markdown](https://verifymcp.io/servers/steadyscrape-seo-data-mcp/seo-mcp.md), [page](https://verifymcp.io/servers/steadyscrape-seo-data-mcp/seo-mcp)

## Channel facts

- Endpoint: `https://mcp.steadyscrape.dev/seo/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## 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 2026-11-21.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, 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**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1296 tokens (~144/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 3/100
  - Stability observed for 1 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 97/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 92% 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 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 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 SEO Data MCP (SteadyScrape) server?

SEO Data MCP (SteadyScrape) is a hosted endpoint at https://mcp.steadyscrape.dev/seo/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 steadyscrape-seo-data-mcp 'https://mcp.steadyscrape.dev/seo/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "steadyscrape-seo-data-mcp": {
      "url": "https://mcp.steadyscrape.dev/seo/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "steadyscrape-seo-data-mcp": {
      "type": "http",
      "url": "https://mcp.steadyscrape.dev/seo/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.steadyscrape-seo-data-mcp]
url = "https://mcp.steadyscrape.dev/seo/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add steadyscrape-seo-data-mcp --url 'https://mcp.steadyscrape.dev/seo/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  steadyscrape-seo-data-mcp:
    url: "https://mcp.steadyscrape.dev/seo/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "steadyscrape-seo-data-mcp": {
      "Transport": "http",
      "Url": "https://mcp.steadyscrape.dev/seo/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add steadyscrape-seo-data-mcp -t streamable-http -u 'https://mcp.steadyscrape.dev/seo/mcp'
```

### Other

```json
{
  "mcpServers": {
    "steadyscrape-seo-data-mcp": {
      "type": "http",
      "url": "https://mcp.steadyscrape.dev/seo/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 65, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-20 (score 64)

First indexed and scored.

## MCP tools (9)

### `keyword_metrics` (~126 tokens)

Keyword metrics (Google)

Google search volume, CPC, competition, keyword difficulty (0-100), search intent and the last 12 months of volume for up to 100 keywords in one country. Keywords without data are listed in noData and not charged. Billed per started block of 10 keywords that have data.

Input parameters:

- `country` (string): 2-letter country code (US, GB, DE...) or English name. Default US.
- `keywords` (array, required): 1-100 keywords.
- `language` (string): Language code, e.g. en, es, de. Default en.

### `google_serp` (~193 tokens)

Google search results (live SERP)

Live Google organic results for one keyword: position, title, URL, domain and snippet, plus which SERP features appear (AI Overview, People Also Ask, local pack, video...) and the AI Overview text. Optionally give target_domain to get that domain's best position (rank check). Billed per 10 results of depth.

Input parameters:

- `country` (string): 2-letter country code (US, GB, DE...) or English name. Default US.
- `depth` (integer): Results to fetch: 10-100 (default 10). Deeper is slower (100 takes ~15 s).
- `device` (string): Default desktop.
- `keyword` (string, required): The search query.
- `language` (string): Language code, e.g. en, es, de. Default en.
- `target_domain` (string): Optional domain to find in the results, e.g. example.com.

### `rank_check` (~177 tokens)

Rank check for up to 10 keywords (Google)

Where one domain ranks on live Google for up to 10 keywords in one country: best position, ranking URL and the top 3 domains for each keyword, plus SERP features. Same data and price as google_serp, billed per 10 results of depth for each keyword that returns results.

Input parameters:

- `country` (string): 2-letter country code (US, GB, DE...) or English name. Default US.
- `depth` (integer): Results checked per keyword: 10-100 (default 10).
- `device` (string): Default desktop.
- `keywords` (array, required): 1-10 search queries.
- `language` (string): Language code, e.g. en, es, de. Default en.
- `target_domain` (string, required): Domain to find, e.g. example.com (subdomains count).

### `domain_overview` (~123 tokens)

Domain SEO overview

For up to 100 domains: estimated monthly organic traffic and number of ranking keywords in one country (Google), paid keywords, plus backlink profile: domain rank (0-1000), backlinks, referring domains, spam score, first seen. Billed per started block of 10 domains that have data.

Input parameters:

- `country` (string): 2-letter country code (US, GB, DE...) or English name. Default US.
- `domains` (array, required)
- `language` (string): Language code, e.g. en, es, de. Default en.

### `ranked_keywords` (~138 tokens)

Keywords a domain ranks for

The Google keywords a domain (or URL) ranks for in one country, sorted by estimated traffic: keyword, position, ranking URL, search volume, CPC and estimated visits. Up to 100 keywords per call, plus position distribution totals. Billed per call with data.

Input parameters:

- `country` (string): 2-letter country code (US, GB, DE...) or English name. Default US.
- `domain` (string, required): Domain (example.com) or page URL.
- `language` (string): Language code, e.g. en, es, de. Default en.
- `limit` (integer): Keywords to return (default 20).

### `backlinks` (~120 tokens)

Backlinks / referring domains

Backlinks or referring domains pointing to a domain or page URL, strongest first: linking page/domain, anchor, dofollow, first/last seen and rank. Up to 100 rows per call, plus the target's totals. Billed per call with data.

Input parameters:

- `dofollow_only` (boolean): Backlinks mode only: return only dofollow links (default false).
- `limit` (integer): Rows to return (default 20).
- `mode` (string): Default backlinks.
- `target` (string, required): Domain (example.com) or page URL.

### `google_trends` (~114 tokens)

Google Trends

Google Trends interest over time (0-100) for up to 5 keywords compared, in a country or worldwide, for web, YouTube, news, images or shopping search, plus each keyword's average. Billed per call with data.

Input parameters:

- `country` (string): 2-letter country code or 'worldwide'. Default US.
- `keywords` (array, required)
- `search_type` (string): Default web (froogle = shopping).
- `time_range` (string): Default past_12_months.

### `youtube_search` (~118 tokens)

YouTube search results

YouTube search results for a query in ranked order: video ID, title, channel, views, publish date, duration and whether it is a Short. Up to 40 results. Billed per 20 results of depth.

Input parameters:

- `country` (string): 2-letter country code (US, GB, DE...) or English name. Default US.
- `language` (string): Language code, e.g. en, es, de. Default en.
- `max_results` (integer): Default 20.
- `query` (string, required)

### `youtube_video` (~114 tokens)

YouTube video stats and transcript

Public stats for one YouTube video (views, likes, comment count, channel subscribers, tags, category, description, duration, publish date) and optionally its transcript. Billed per video; the transcript is billed separately and only if the video has captions.

Input parameters:

- `include_transcript` (boolean): Also return the captions text (default false).
- `language` (string): Language code, e.g. en, es, de. Default en.
- `video` (string, required): YouTube URL or 11-character video ID.

## Diagnostics

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

## Score history

- 2026-11-21: 65
- 2026-11-20: 64

## Common questions

### What is the SEO Data MCP (SteadyScrape) server?

SEO Data MCP (SteadyScrape) is listed in the public MCP registry as io.github.steadyscrape/seo-data-mcp. Keyword volume, live SERP ranks, domain traffic, ranked keywords, backlinks, Google Trends, YouTube. This page covers its hosted endpoint (https://mcp.steadyscrape.dev/seo/mcp).

### Is the SEO Data MCP (SteadyScrape) server safe to use?

SEO Data MCP (SteadyScrape) scores 65 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 SEO Data MCP (SteadyScrape) server expose?

SEO Data MCP (SteadyScrape) exposes 9 tools: keyword_metrics, google_serp, rank_check, domain_overview, ranked_keywords, and 4 more. Their descriptions and schemas cost roughly 1,223 tokens of context every time the server is loaded.

### Does the SEO Data MCP (SteadyScrape) server require authentication?

No. We connected to SEO Data MCP (SteadyScrape) without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the SEO Data MCP (SteadyScrape) server still maintained?

SEO Data MCP (SteadyScrape) 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 SEO Data MCP (SteadyScrape) server?

VerifyMCP ran 12 checks on SEO Data MCP (SteadyScrape), covering TLS certificate, Authorization, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about SEO Data MCP (SteadyScrape): HTTPS. 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://mcp.steadyscrape.dev/seo/mcp
- Repository: https://github.com/steadyscrape/seo-data-mcp
- Website: https://mcp.steadyscrape.dev/seo
- Changelog RSS feed: https://verifymcp.io/servers/steadyscrape-seo-data-mcp/seo-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/steadyscrape-seo-data-mcp/seo-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/steadyscrape-seo-data-mcp/seo-mcp.json
- HTML version of this page: https://verifymcp.io/servers/steadyscrape-seo-data-mcp/seo-mcp
