# Semscraper (remote · mcp.semscraper.com)

Real Google and Google Maps SERPs for AI assistants: pixel positions, AI Overviews and sources.

- Trust score: 72/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- remote · `mcp.semscraper.com`: 72/100 (this document), [markdown](https://verifymcp.io/servers/com-semscraper-semscraper/mcp.md), [page](https://verifymcp.io/servers/com-semscraper-semscraper/mcp)

## Channel facts

- Endpoint: `https://mcp.semscraper.com/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 2026-10-23.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - 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.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 61/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2520 tokens (~315/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 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.
  - We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 9 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 Semscraper MCP server?

Semscraper is a hosted endpoint at https://mcp.semscraper.com/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-semscraper-semscraper 'https://mcp.semscraper.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-semscraper-semscraper": {
      "url": "https://mcp.semscraper.com/mcp"
    }
  }
}
```

### VS Code

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

### Codex

```toml
[mcp_servers.com-semscraper-semscraper]
url = "https://mcp.semscraper.com/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add com-semscraper-semscraper --url 'https://mcp.semscraper.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-semscraper-semscraper:
    url: "https://mcp.semscraper.com/mcp"
```

### Netclaw

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

### Vellum

```bash
assistant mcp add com-semscraper-semscraper -t streamable-http -u 'https://mcp.semscraper.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-semscraper-semscraper": {
      "type": "http",
      "url": "https://mcp.semscraper.com/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.

### 2026-10-23 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-21 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-18 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-17 (score 69, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-16 (score 69, +36)

- [security improvement] Transport: unverified → pass
- [security improvement] Injection markers: unverified → pass
- [security improvement] Authorization: fail → partial
- [security] First check of Judged manipulation: pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 100

### 2026-10-10 (score 33)

First indexed and scored.

## MCP tools (8)

### `google_search` (~699 tokens)

Google Search results

Collects the real Google results page (SERP) for one or more keywords, rendered in a real browser, and returns every block (organic results, ads, local pack, People Also Ask, AI Overview with its citations and sources...) with, for each item, its rank in its block (rank_type), its rank on the page (rank_serp), its Google page and its pixel position. Use it to know what Google actually shows for a query, in a given country, language, city and device. Paid from the account balance: about EUR 0.0003 per keyword for the first page, EUR 0.0002 per extra page. Takes about 30 seconds per keyword (about a minute for 10 pages); the tool waits for the results. Returns titles, snippets and URLs, not the full content of the pages.

Input parameters:

- `blocks` (array): Only return these result blocks, e.g. ["organic"] or ["ai_overview*"] (a trailing * matches a prefix). Block types: organic, paid_top, paid_bottom, local_pack, people_also_ask, featured_snippet, know…
- `depth` (integer): Number of Google result pages to collect, 1 (about 10 results) to 10 (about 100). Each extra page costs more and takes longer.
- `device` (string): Device to emulate.
- `domain` (string): Only return the positions of this domain (e.g. "example.com", subdomains included) in every block, with its best organic rank and whether it appears in the AI Overview, instead of the whole SERP. Muc…
- `geolocation` (string): Optional city-level geolocation: "City, Region, Country" (e.g. "Lyon, Rhone, France") or a GPS position "latitude,longitude" (e.g. "43.7102,7.2620").
- `keywords` (array, required): Keywords to search, one search per keyword (max 100). Google operators work (site:, inurl:, intitle:, quotes, -term). No comma inside a keyword.
- `language` (string, required): Interface language code, e.g. fr, en, de, es, it, pt, ja. Must form a valid pair with location (see list_google_versions).
- `location` (string, required): Google version as a country code: fr for google.fr, de for google.de, br for google.com.br, jp for google.co.jp, us for google.com. Must form a valid pair with language (see list_google_versions).
- `max_items_per_block` (integer): Maximum number of items returned per block, to keep the answer short.
- `priority` (integer): Priority in the account queue, 1 to 10 (10 first). Use a high value for a few urgent searches when a large batch is already running.
- `wait_seconds` (integer): How long this call waits for the results, in seconds (default 45, max 55). Searches still running are returned in pending_ids: fetch them with get_serp_results. Use 0 to start a large batch and retur…

### `google_maps` (~519 tokens)

Google Maps results

Collects the listings of a Google Maps search for one or more keywords, in the order Google Maps shows them, from a given place. Each listing comes with its rank, name (title), CID, category (type), address, website, rating, review count, opening status and the snippet shown. Use it for local SEO, local competition and market research. Paid from the account balance, same price as google_search. Returns rating and review count, not the full text of reviews.

Input parameters:

- `depth` (integer): Number of Google result pages to collect, 1 (about 10 results) to 10 (about 100). Each extra page costs more and takes longer.
- `domain` (string): Only return the positions of this domain (e.g. "example.com", subdomains included) in every block, with its best organic rank and whether it appears in the AI Overview, instead of the whole SERP. Muc…
- `geolocation` (string): Place the search is made from: "City, Region, Country" or "latitude,longitude", with an optional zoom suffix ("43.7102,7.2620,16z"). Strongly recommended: Maps results depend on the location.
- `keywords` (array, required): Keywords to search, one search per keyword (max 100). Google operators work (site:, inurl:, intitle:, quotes, -term). No comma inside a keyword.
- `language` (string): Interface language code, e.g. fr, en, de, es, it, pt, ja. Must form a valid pair with location (see list_google_versions).
- `location` (string): Google version as a country code: fr for google.fr, de for google.de, br for google.com.br, jp for google.co.jp, us for google.com. Must form a valid pair with language (see list_google_versions).
- `max_items_per_block` (integer): Maximum number of items returned per block, to keep the answer short.
- `priority` (integer): Priority in the account queue, 1 to 10 (10 first). Use a high value for a few urgent searches when a large batch is already running.
- `wait_seconds` (integer): How long this call waits for the results, in seconds (default 45, max 55). Searches still running are returned in pending_ids: fetch them with get_serp_results. Use 0 to start a large batch and retur…

### `get_serp_results` (~285 tokens)

Get results by ID

Returns searches already created (google_search or google_maps), by their IDs (serp_...), e.g. the pending_ids of a previous call. Free: the searches were paid when created.

Input parameters:

- `blocks` (array): Only return these result blocks, e.g. ["organic"] or ["ai_overview*"] (a trailing * matches a prefix). Block types: organic, paid_top, paid_bottom, local_pack, people_also_ask, featured_snippet, know…
- `domain` (string): Only return the positions of this domain (e.g. "example.com", subdomains included) in every block, with its best organic rank and whether it appears in the AI Overview, instead of the whole SERP. Muc…
- `ids` (array, required): IDs returned by a previous search (serp_...).
- `max_items_per_block` (integer): Maximum number of items returned per block, to keep the answer short.
- `wait_seconds` (integer): How long this call waits for searches still running, in seconds (default 45, max 55). Call again while pending_ids remain.

### `ai_overview_sources` (~171 tokens)

AI Overview sources

Computes, on the server, which domains Google cites in the AI Overviews of searches already created (google_search IDs): for each domain, the number of keywords where it is cited, the number of mentions, the keywords and its best position on the page. Also returns how many searches have an AI Overview. Free. Best tool to answer "which sites does Google cite in its AI Overviews on these keywords": one small answer instead of every SERP. Based on source URLs, not on brand names.

Input parameters:

- `ids` (array, required): IDs of google_search searches (serp_...).
- `top` (integer): Number of domains returned, most cited first.
- `wait_seconds` (integer): How long to wait for searches still running, in seconds (default 45, max 55).

### `list_searches` (~205 tokens)

Search history

Lists the searches of the account, most recent first (ID, engine, keyword, device, location, language, depth, geolocation, status, whether the results were already fetched, cost, creation date), without their results. Free. Covers every search made with the account, through this server or the API. Use it to find IDs (e.g. "the last 10 searches", "today's searches"), and whenever a google_search or google_maps call failed, timed out or lost its answer: the searches were probably created and paid already, so fetch them with get_serp_results instead of searching again.

Input parameters:

- `cursor` (string): next_cursor from a previous call, to get the following page.
- `date` (string): Only the searches created that day, format YYYY-MM-DD (server time, Europe/Paris).
- `limit` (integer): Number of searches returned (default 20).
- `status` (string): Only the searches with this status.

### `get_balance` (~23 tokens)

Account balance

Returns the balance of the Semscraper account, in euros. Free.

### `list_google_versions` (~88 tokens)

Google versions

Lists the supported Google versions as location / language pairs (186 Google domains, 117 languages), to pick valid location and language values. Free. Filter with a country domain, a code or a language name to keep the answer short.

Input parameters:

- `filter` (string): Text to look for in the domain, codes or language name, e.g. "google.de", "br", "Deutsch".

### `get_queue_status` (~47 tokens)

Queue status

Returns how many searches of the account are pending, processing or done. Free. The account has its own queue: the robots serve accounts in turn, so a large batch flows through gradually.

## Diagnostics

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

## Score history

- 2026-10-23: 72
- 2026-10-22: 71
- 2026-10-21: 71
- 2026-10-20: 70
- 2026-10-19: 70
- 2026-10-18: 70
- 2026-10-17: 69
- 2026-10-16: 69
- 2026-10-15: 33
- 2026-10-14: 33
- 2026-10-13: 33
- 2026-10-12: 33
- 2026-10-10: 33

## Common questions

### What is the Semscraper MCP server?

Semscraper is an MCP server listed in the public MCP registry as com.semscraper/semscraper. Real Google and Google Maps SERPs for AI assistants: pixel positions, AI Overviews and sources. This page covers its hosted endpoint (https://mcp.semscraper.com/mcp).

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

Semscraper scores 72 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 Semscraper MCP server expose?

Semscraper exposes 8 tools: google_search, google_maps, get_serp_results, ai_overview_sources, list_searches, and 3 more. Their descriptions and schemas cost roughly 2,037 tokens of context every time the server is loaded.

### Does the Semscraper MCP server require authentication?

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

### Is the Semscraper MCP server still maintained?

Semscraper is still listed as active in the MCP registry. We last reached this channel on 23 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://mcp.semscraper.com/mcp
- Authorisation metadata: https://mcp.semscraper.com/.well-known/oauth-protected-resource/mcp
- Website: https://www.semscraper.com/en/mcp
- Changelog RSS feed: https://verifymcp.io/servers/com-semscraper-semscraper/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-semscraper-semscraper/mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-semscraper-semscraper/mcp