# Litescrape (npm · litescrape-mcp-server)

Google, Bing, DuckDuckGo and Google Maps search results, free without an API key.

- Trust score: 78/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `mcp.litescrape.com`: 63/100, [markdown](https://verifymcp.io/servers/com-litescrape-litescrape-mcp-server/mcp.md), [page](https://verifymcp.io/servers/com-litescrape-litescrape-mcp-server/mcp)
- npm · `litescrape-mcp-server`: 78/100 (this document), [markdown](https://verifymcp.io/servers/com-litescrape-litescrape-mcp-server/litescrape-mcp-server.md), [page](https://verifymcp.io/servers/com-litescrape-litescrape-mcp-server/litescrape-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `litescrape-mcp-server`
- Version: `0.2.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 96 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to litescrape/litescrape-mcp-server).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 4 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 57/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 3445 tokens (~382/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**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 97% 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.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

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

Litescrape runs locally as an npm package, launched with npx -y litescrape-mcp-server. 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 com-litescrape-litescrape-mcp-server -- npx -y litescrape-mcp-server
```

### Cursor

```json
{
  "mcpServers": {
    "com-litescrape-litescrape-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "litescrape-mcp-server"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-litescrape-litescrape-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "litescrape-mcp-server"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add com-litescrape-litescrape-mcp-server -- npx -y litescrape-mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-litescrape-litescrape-mcp-server": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "litescrape-mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-litescrape-litescrape-mcp-server --command npx --arg -y --arg litescrape-mcp-server
```

### Hermes

```yaml
mcp_servers:
  com-litescrape-litescrape-mcp-server:
    command: "npx"
    args: ["-y", "litescrape-mcp-server"]
```

### Netclaw

```json
{
  "McpServers": {
    "com-litescrape-litescrape-mcp-server": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "litescrape-mcp-server"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-litescrape-litescrape-mcp-server -t stdio -c npx -a -y litescrape-mcp-server
```

### Other

```json
{
  "mcpServers": {
    "com-litescrape-litescrape-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "litescrape-mcp-server"
      ]
    }
  }
}
```

## 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.

### 2026-09-16 (score 78, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-15 (score 63)

First indexed and scored.

## MCP tools (9)

### `search` (~205 tokens)

Web search

Search the web through Google and return ranked organic results (title, link, snippet) as JSON. Fast mode: no Knowledge Graph, ads or AI modules; use google_search for the full results page. Free without an API key (shares the google_search allowance).

Input parameters:

- `gl` (string): Two-letter country for localization, e.g. "us"
- `hl` (string): Language code such as "en" or "en-GB"; default en
- `location` (string): Named search origin such as "Austin, Texas"; conflicts with uule and lat/lon
- `num` (integer): Requested result count, 1-100; Google may return fewer
- `q` (string, required): What to search for
- `result_groups` (array): Return only these top-level result groups, e.g. ["organic_results", "knowledge_graph"]; omit for the complete response. search_metadata is always kept
- `start` (integer): Result offset for pagination

### `google_search` (~577 tokens)

Google Search

Fetch a first-party Google Search results page as JSON: organic_results plus whichever modules Google served (knowledge_graph, answer_box, ai_overview, ads, related_questions, related_searches, local_results, top_stories, inline_videos and more). Supports localization, verticals (news, videos, local, shopping, patents), date filters and site restriction. Free without an API key: 25 calls per network per day.

Input parameters:

- `as_qdr` (string): Date range: d, w, m or y with an optional count, e.g. d7 for the past week
- `as_sitesearch` (string): Restrict results to this hostname
- `cr` (string): Country restrict such as countryUS|countryCA
- `device` (string): Layout to request; default desktop
- `fast_mode` (boolean): true returns only organic_results (faster and smaller); skips AI Overview, Knowledge Graph, ads and every other module
- `filter` (string): 0 disables duplicate-content filtering
- `gl` (string): Two-letter country for localization, e.g. "us"
- `google_domain` (string): Google domain such as google.co.uk; default google.com
- `hl` (string): Language code such as "en" or "en-GB"; default en
- `kgmid` (string): Knowledge Graph machine ID such as /m/0k8z
- `lat` (number): Latitude; supply together with lon
- `location` (string): Named search origin such as "Austin, Texas"; conflicts with uule and lat/lon
- `lon` (number): Longitude; supply together with lat
- `lr` (string): Language restrict such as lang_en|lang_fr
- `ludocid` (string): Google CID of a local entity, for a targeted lookup
- `nfpr` (string): 1 disables spelling auto-correction
- `num` (integer): Requested result count, 1-100; Google may return fewer
- `q` (string): Search query; required unless ludocid or kgmid is supplied
- `radius` (number): Radius in meters around the location or coordinates
- `result_groups` (array): Return only these top-level result groups, e.g. ["organic_results", "knowledge_graph"]; omit for the complete response. search_metadata is always kept
- `safe` (string): SafeSearch
- `start` (integer): Result offset for pagination
- `tbm` (string): Vertical: lcl local, vid videos, nws news, shop shopping, pts patents
- `tbs` (string): Google search-filter string, e.g. qdr:w for the past week
- `uule` (string): Pre-encoded Google location token; conflicts with location

### `bing_search` (~241 tokens)

Bing Search

Fetch a Bing web search results page as JSON: organic_results plus the modules Bing served (answer_box, knowledge_graph, copilot_answer, ads, related_questions, inline_videos, top_stories and more). Free without an API key: 50 calls per network per day.

Input parameters:

- `cc` (string): Two-letter country code; conflicts with mkt
- `device` (string): Layout to request; default desktop
- `filters` (string): Native Bing display or date filters
- `first` (integer): One-based organic result offset for pagination; default 1
- `lat` (number): Latitude; supply together with lon
- `location` (string): City-level search origin
- `lon` (number): Longitude; supply together with lat
- `mkt` (string): Market such as en-US; conflicts with cc
- `q` (string, required): Search query; Bing operators are preserved
- `result_groups` (array): Return only these top-level result groups, e.g. ["organic_results", "knowledge_graph"]; omit for the complete response. search_metadata is always kept
- `safeSearch` (string): Default moderate

### `duckduckgo_search` (~204 tokens)

DuckDuckGo Search

Fetch ranked DuckDuckGo web results (organic_results with title, link, snippet) with region, safety and date controls. Free without an API key: 50 calls per network per day.

Input parameters:

- `df` (string): Date filter: d, w, m, y, or YYYY-MM-DD..YYYY-MM-DD
- `kl` (string): Region and language token such as us-en
- `m` (integer): Result count 1-50; cannot be combined with search_assist
- `q` (string, required): Search query
- `result_groups` (array): Return only these top-level result groups, e.g. ["organic_results", "knowledge_graph"]; omit for the complete response. search_metadata is always kept
- `safe` (string): 1 strict, -1 moderate (default), -2 off
- `search_assist` (boolean): Default true; cannot be combined with m
- `start` (integer): Result offset

### `google_maps` (~489 tokens)

Google Maps

Search Google Maps for places (local_results with name, address, rating, reviews, hours, phone, website, coordinates) or fetch one exact place (place_results) by place_id, data_cid or data sequence. Filter by price, rating and opening hours. Free without an API key: 50 calls per network per day.

Input parameters:

- `data` (string): Exact place by Google Maps data sequence
- `data_cid` (string): Exact place by decimal Google CID
- `gl` (string): Two-letter country for localization, e.g. "us"
- `google_domain` (string): Google domain such as google.co.uk; default google.com
- `hl` (string): Language code such as "en" or "en-GB"; default en
- `lat` (number): Latitude; supply together with lon
- `ll` (string): Viewport as @lat,lon,14z or @lat,lon,5000m
- `location` (string): Named search origin such as "Austin, Texas"; conflicts with uule and lat/lon
- `lon` (number): Longitude; supply together with lat
- `m` (number): Radius in meters; use with location or lat/lon
- `max_price` (integer): Price level upper bound
- `min_price` (integer): Price level lower bound
- `min_rating` (string): Minimum rating preference
- `nearby` (boolean): Restrict results to places near the viewport
- `open_at_hour` (integer): Hour 0-23; requires open_on_day
- `open_on_day` (string)
- `open_state` (string): Open now, or open 24 hours; cannot combine with open_on_day
- `place_id` (string): Exact place by Google place ID
- `q` (string): Search text; required for type=search
- `result_groups` (array): Return only these top-level result groups, e.g. ["organic_results", "knowledge_graph"]; omit for the complete response. search_metadata is always kept
- `start` (integer): Native Maps result offset
- `type` (string): search (default) for a query, or place for one exact place identified by place_id, data_cid or data
- `z` (number): Zoom 3-30; use with location or lat/lon

### `google_ai_overview` (~502 tokens)

Google AI Overview

Return only the AI Overview Google generates for a search (ai_overview with ordered text_blocks and cited references), or null when Google shows none. Accepts the google_search parameters. Requires an API key.

Input parameters:

- `as_qdr` (string): Date range: d, w, m or y with an optional count, e.g. d7 for the past week
- `as_sitesearch` (string): Restrict results to this hostname
- `cr` (string): Country restrict such as countryUS|countryCA
- `device` (string): Layout to request; default desktop
- `filter` (string): 0 disables duplicate-content filtering
- `gl` (string): Two-letter country for localization, e.g. "us"
- `google_domain` (string): Google domain such as google.co.uk; default google.com
- `hl` (string): Language code such as "en" or "en-GB"; default en
- `kgmid` (string): Knowledge Graph machine ID such as /m/0k8z
- `lat` (number): Latitude; supply together with lon
- `location` (string): Named search origin such as "Austin, Texas"; conflicts with uule and lat/lon
- `lon` (number): Longitude; supply together with lat
- `lr` (string): Language restrict such as lang_en|lang_fr
- `ludocid` (string): Google CID of a local entity, for a targeted lookup
- `nfpr` (string): 1 disables spelling auto-correction
- `num` (integer): Requested result count, 1-100; Google may return fewer
- `q` (string): Search query; required unless ludocid or kgmid is supplied
- `radius` (number): Radius in meters around the location or coordinates
- `result_groups` (array): Return only these top-level result groups, e.g. ["organic_results", "knowledge_graph"]; omit for the complete response. search_metadata is always kept
- `safe` (string): SafeSearch
- `start` (integer): Result offset for pagination
- `tbm` (string): Vertical: lcl local, vid videos, nws news, shop shopping, pts patents
- `tbs` (string): Google search-filter string, e.g. qdr:w for the past week
- `uule` (string): Pre-encoded Google location token; conflicts with location

### `google_ai_mode` (~318 tokens)

Google AI Mode

Ask Google AI Mode a question and return its generated answer (ordered text_blocks: paragraphs, headings, lists, tables, code) with the sources it cited (references). Set continuable to get a token for follow-up questions; image_url adds a picture to the prompt. Slow: answers are generated per request. Requires an API key.

Input parameters:

- `continuable` (boolean): Return a subsequent_request_token so the conversation can continue
- `device` (string): Layout to request; default desktop
- `gl` (string): Two-letter country for localization, e.g. "us"
- `google_domain` (string): Google domain such as google.co.uk; default google.com
- `hl` (string): Language code such as "en" or "en-GB"; default en
- `image_url` (string): Public http(s) image to include in the prompt; cannot combine with a token
- `location` (string): Named search origin such as "Austin, Texas"; conflicts with uule and lat/lon
- `q` (string, required): The question to ask
- `result_groups` (array): Return only these top-level result groups, e.g. ["organic_results", "knowledge_graph"]; omit for the complete response. search_metadata is always kept
- `subsequent_request_token` (string): Token from a previous continuable answer; send with a new q. Expires after 30 minutes; cannot combine with image_url
- `uule` (string): Pre-encoded Google location token; conflicts with location

### `google_shopping` (~357 tokens)

Google Shopping

Search Google Shopping and return the product grid (shopping_results with title, price, source, rating, thumbnail), category blocks, sponsored listings and the refinement chips Google renders (filters). Price bounds, sale, shipping and small business refinements are mutually exclusive; sort_by combines with one of them. Requires an API key.

Input parameters:

- `device` (string): Layout to request; default desktop
- `free_shipping` (boolean)
- `gl` (string): Two-letter country for localization, e.g. "us"
- `google_domain` (string): Google domain such as google.co.uk; default google.com
- `hl` (string): Language code such as "en" or "en-GB"; default en
- `location` (string): Named search origin such as "Austin, Texas"; conflicts with uule and lat/lon
- `max_price` (number): Upper price bound
- `min_price` (number): Lower price bound
- `num` (integer): Product count, 1-100
- `on_sale` (boolean)
- `q` (string): Product query; required unless shoprs is supplied
- `result_groups` (array): Return only these top-level result groups, e.g. ["organic_results", "knowledge_graph"]; omit for the complete response. search_metadata is always kept
- `shoprs` (string): Refinement token from a previous response's filters
- `small_business` (boolean)
- `sort_by` (string): 1 price low to high, 2 price high to low, 3 rating, 4 relevance
- `start` (integer): Result offset
- `uule` (string): Pre-encoded Google location token; conflicts with location

### `google_reviews` (~347 tokens)

Google Reviews

Return the Google Maps reviews of one place (reviews with rating, snippet, author, date, likes, owner response, guided details and dining subratings) plus place_info. Identify the place by place_id or data_id from a google_maps result. Sort, filter by topic or text, and follow pagination.next_page_token for more. Requires an API key.

Input parameters:

- `data_id` (string): Google data ID such as 0x89c2...:0x...; exactly one of place_id and data_id
- `gl` (string): Two-letter country for localization, e.g. "us"
- `hl` (string): Language code such as "en" or "en-GB"; default en
- `next_page_token` (string): pagination.next_page_token from the previous response; keep the same place, sort and filters
- `num` (integer): Reviews to return: 1-100 on a first unfiltered request (default 8), 1-20 with topic_id, query or next_page_token (default 10)
- `place_id` (string): Google place ID such as ChIJ...; exactly one of place_id and data_id
- `query` (string): Keep reviews mentioning this text; conflicts with topic_id
- `result_groups` (array): Return only these top-level result groups, e.g. ["organic_results", "knowledge_graph"]; omit for the complete response. search_metadata is always kept
- `sort_by` (string): Order: qualityScore (most relevant, default), newestFirst, ratingHigh, ratingLow
- `topic_id` (string): Keep reviews on one Google review topic; conflicts with query

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/com-litescrape-litescrape-mcp-server/litescrape-mcp-server#diagnostics

## Score history

- 2026-09-20: 78
- 2026-09-19: 78
- 2026-09-18: 78
- 2026-09-17: 78
- 2026-09-16: 78
- 2026-09-15: 63

## Common questions

### What is the Litescrape MCP server?

Litescrape is an MCP server listed in the public MCP registry as com.litescrape/litescrape-mcp-server. Google, Bing, DuckDuckGo and Google Maps search results, free without an API key. This page covers its npm package (litescrape-mcp-server).

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

Litescrape scores 78 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 Litescrape MCP server expose?

Litescrape exposes 9 tools: search, google_search, bing_search, duckduckgo_search, google_maps, and 4 more. Their descriptions and schemas cost roughly 3,240 tokens of context every time the server is loaded.

### Is the Litescrape MCP server still maintained?

Litescrape 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.

### What licence is the Litescrape MCP server under?

Litescrape declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/litescrape-mcp-server
- Socket report: https://socket.dev/npm/package/litescrape-mcp-server
- Repository: https://github.com/litescrape/litescrape-mcp-server
- Website: https://litescrape.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-litescrape-litescrape-mcp-server/litescrape-mcp-server.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-litescrape-litescrape-mcp-server/litescrape-mcp-server.json
- HTML version of this page: https://verifymcp.io/servers/com-litescrape-litescrape-mcp-server/litescrape-mcp-server