# io.oxylabs/oxylabs-mcp (remote · mcp.oxylabs.io)

Fetch and process content from specified URLs & sources using the Oxylabs Web Scraper API.

- Trust score: 75/100 (medium)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `mcp.oxylabs.io`: 75/100 (this document), [markdown](https://verifymcp.io/servers/io-oxylabs-oxylabs-mcp/mcp.md), [page](https://verifymcp.io/servers/io-oxylabs-oxylabs-mcp/mcp)
- pypi · `oxylabs-mcp`: 21/100, [markdown](https://verifymcp.io/servers/io-oxylabs-oxylabs-mcp/oxylabs-mcp.md), [page](https://verifymcp.io/servers/io-oxylabs-oxylabs-mcp/oxylabs-mcp)

## Channel facts

- Endpoint: `https://mcp.oxylabs.io/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.9.1`

## 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**: 57/100
  - 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 10 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.
  - 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**: 55/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2975 tokens (~297/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **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.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 10 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 io.oxylabs/oxylabs-mcp server?

io.oxylabs/oxylabs-mcp is a hosted endpoint at https://mcp.oxylabs.io/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 io-oxylabs-oxylabs-mcp 'https://mcp.oxylabs.io/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "io-oxylabs-oxylabs-mcp": {
      "url": "https://mcp.oxylabs.io/mcp"
    }
  }
}
```

### VS Code

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

### Codex

```toml
[mcp_servers.io-oxylabs-oxylabs-mcp]
url = "https://mcp.oxylabs.io/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add io-oxylabs-oxylabs-mcp --url 'https://mcp.oxylabs.io/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  io-oxylabs-oxylabs-mcp:
    url: "https://mcp.oxylabs.io/mcp"
```

### Netclaw

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

### Vellum

```bash
assistant mcp add io-oxylabs-oxylabs-mcp -t streamable-http -u 'https://mcp.oxylabs.io/mcp'
```

### Other

```json
{
  "mcpServers": {
    "io-oxylabs-oxylabs-mcp": {
      "type": "http",
      "url": "https://mcp.oxylabs.io/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.

### 2026-09-10 (score 75, +1)

- [security] Stability: 0.97 → pass

### 2026-09-08 (score 74, +1)

- [functional] Server version: 0.9.2 → 0.9.3

### 2026-09-06 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-04 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-02 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-31 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-28 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-26 (score 68, +2)

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

## MCP tools (10)

### `ai_crawler` (~307 tokens)

Tool useful for crawling a website from starting url and returning data in a specified format.

Schema is required only if output_format is json, csv or toon.
'render_javascript' is used to render javascript heavy websites.
'return_sources_limit' is used to limit the number of sources to return,
for example if you expect results from single source, you can set it to 1.

Input parameters:

- `geo_location`: Two letter ISO country code to use for the crawl proxy.
- `output_format` (string): The format of the output. If json, csv or toon, the schema is required. Markdown returns full text of the page. CSV returns data in CSV format. Toon(Token-Oriented Object Notation) returns data in To…
- `render_javascript` (boolean): Whether to render the HTML of the page using javascript. Much slower, therefore use it only for websites that require javascript to render the page. Unless user asks to use it, first try to crawl the…
- `return_sources_limit` (integer): The maximum number of sources to return.
- `schema`: The JSON schema to use for structured data extraction from the crawled pages. Only required if output_format is json, csv or toon.
- `url` (string, required): The URL from which crawling will be started.
- `user_prompt` (string, required): What information user wants to extract from the domain.

Output parameters:

- `result` (string)

### `ai_scraper` (~238 tokens)

Scrape the contents of the web page and return the data in the specified format.

Schema is required only if output_format is json or csv.
'render_javascript' is used to render javascript heavy websites.

Input parameters:

- `geo_location`: Two letter ISO country code to use for the scrape proxy.
- `output_format` (string): The format of the output. If json, csv or toon, the schema is required. Markdown returns full text of the page. CSV returns data in CSV format, tabular like data. Toon(Token-Oriented Object Notation)…
- `render_javascript` (boolean): Whether to render the HTML of the page using javascript. Much slower, therefore use it only for websites that require javascript to render the page.Unless user asks to use it, first try to scrape the…
- `schema`: The JSON schema to use for structured data extraction from the scraped page. Only required if output_format is json, csv or toon.
- `url` (string, required): The URL to scrape

Output parameters:

- `result` (string)

### `ai_browser_agent` (~215 tokens)

Run the browser agent and return the data in the specified format.

This tool is useful if you need navigate around the website and do some actions.
It allows navigating to any url, clicking on links, filling forms, scrolling, etc.
Finally it returns the data in the specified format.
Schema is required only if output_format is json, csv or toon.
'task_prompt' describes what browser agent should achieve

Input parameters:

- `geo_location`: Two letter ISO country code to use for the browser proxy.
- `output_format` (string): The output format. Markdown returns full text of the page including links. Toon(Token-Oriented Object Notation) returns data in Toon format, which is optimized for AI agents. If json, csv or toon, th…
- `schema`: The schema to use for the scrape. Only required if output_format is json, csv or toon.
- `task_prompt` (string, required): What browser agent should do.
- `url` (string, required): The URL to start the browser agent navigation from.

Output parameters:

- `result` (string)

### `ai_search` (~194 tokens)

Search the web based on a provided query.

'return_content' is used to return markdown content for each search result. If 'return_content'
    is set to True, you don't need to use ai_scraper to get the content of the search results urls,
    because it is already included in the search results.
if 'return_content' is set to True, prefer lower 'limit' to reduce payload size.

Input parameters:

- `geo_location`: Two letter ISO country code to use for the search proxy.
- `limit` (integer): Maximum number of results to return.
- `query` (string, required): The query to search for.
- `render_javascript` (boolean): Whether to render the HTML of the page using javascript. Much slower, therefore use it only if user asks to use it.First try to search with setting it to False.
- `return_content` (boolean): Whether to return markdown content of the search results.

Output parameters:

- `result` (string)

### `generate_schema` (~33 tokens)

Generate a json schema in openapi format.

Input parameters:

- `app_name` (string, required)
- `user_prompt` (string, required)

Output parameters:

- `result` (string)

### `ai_map` (~230 tokens)

Tool useful for mapping website's URLs.

Input parameters:

- `allow_external_domains` (boolean): Whether to include external domains URLs.
- `allow_subdomains` (boolean): Whether to map subdomains URLs as well.
- `geo_location`: Two letter ISO country code to use for the mapping proxy.
- `limit` (integer): The maximum number of URLs to return.
- `max_crawl_depth` (integer): The maximum depth of the crawl.
- `render_javascript` (boolean): Whether to render the HTML of the page using javascript. Much slower, therefore use it only for websites that require javascript to render the page. Unless user asks to use it, first try to crawl the…
- `search_keywords`: The keywords to use for URLs paths filtering. Keywords are matched as OR condition. Meaning, one keyword is enough to match the url path.
- `url` (string, required): The URL from which URLs mapping will be started.
- `user_prompt`: What kind of URLs user wants to find. Can be used together with 'search_keywords'.

Output parameters:

- `result` (string)

### `universal_scraper` (~279 tokens)

Get a content of any webpage.

Supports browser rendering, parsing of certain webpages
and different output formats.

Input parameters:

- `geo_location`: The geographical location that the result should be adapted for.         Use ISO-3166 country codes.         Examples:             - 'California, United States'             - 'Mexico'…
- `output_format`: The format of the output. Works only when parse parameter is false.             - links - Most efficient when the goal is navigation or finding specific URLs. Use this first when you need to…
- `render`: Whether a headless browser should be used to render the page.         For example:             - 'html' when browser is required to render the page.
- `url` (string, required): Website url to scrape.
- `user_agent_type`: Device type and browser that will be used to determine User-Agent header value.

Output parameters:

- `result` (string)

### `google_search_scraper` (~489 tokens)

Scrape Google Search results.

Supports content parsing, different user agent types, pagination,
domain, geolocation, locale parameters and different output formats.

Input parameters:

- `ad_mode` (boolean): If true will use the Google Ads source optimized for the paid ads.
- `domain`: Domain localization for Google.         Use country top level domains.         For example:             - 'co.uk' for United Kingdom             - 'us' for United States             - 'fr' f…
- `geo_location`: The geographical location that the result should be adapted for.         Use ISO-3166 country codes.         Examples:             - 'California, United States'             - 'Mexico'…
- `limit` (integer): Number of results to retrieve in each page.
- `locale`: Set 'Accept-Language' header value which changes your Google search page web interface language.         Examples:             - 'en-US' for English, United States             - 'de-AT' for…
- `output_format`: The format of the output. Works only when parse parameter is false.             - links - Most efficient when the goal is navigation or finding specific URLs. Use this first when you need to…
- `pages` (integer): Number of pages to retrieve.
- `parse` (boolean): Should result be parsed. If the result is not parsed, the output_format parameter is applied.
- `query` (string, required): URL-encoded keyword to search for.
- `render`: Whether a headless browser should be used to render the page.         For example:             - 'html' when browser is required to render the page.
- `start_page` (integer): Starting page number.
- `user_agent_type`: Device type and browser that will be used to determine User-Agent header value.

Output parameters:

- `result` (string)

### `amazon_search_scraper` (~509 tokens)

Scrape Amazon search results.

Supports content parsing, different user agent types, pagination,
domain, geolocation, locale parameters and different output formats.
Supports Amazon specific parameters such as category id, merchant id, currency.

Input parameters:

- `category_id`: Search for items in a particular browse node (product category).
- `currency`: Currency that will be used to display the prices.
- `domain`: Domain localization for Google.         Use country top level domains.         For example:             - 'co.uk' for United Kingdom             - 'us' for United States             - 'fr' f…
- `geo_location`: The geographical location that the result should be adapted for.         Use ISO-3166 country codes.         Examples:             - 'California, United States'             - 'Mexico'…
- `locale`: Set 'Accept-Language' header value which changes your Google search page web interface language.         Examples:             - 'en-US' for English, United States             - 'de-AT' for…
- `merchant_id`: Search for items sold by a particular seller.
- `output_format`: The format of the output. Works only when parse parameter is false.             - links - Most efficient when the goal is navigation or finding specific URLs. Use this first when you need to…
- `pages` (integer): Number of pages to retrieve.
- `parse` (boolean): Should result be parsed. If the result is not parsed, the output_format parameter is applied.
- `query` (string, required): Keyword to search for.
- `render`: Whether a headless browser should be used to render the page.         For example:             - 'html' when browser is required to render the page.
- `start_page` (integer): Starting page number.
- `user_agent_type`: Device type and browser that will be used to determine User-Agent header value.

Output parameters:

- `result` (string)

### `amazon_product_scraper` (~481 tokens)

Scrape Amazon products.

Supports content parsing, different user agent types, domain,
geolocation, locale parameters and different output formats.
Supports Amazon specific parameters such as currency and getting
more accurate pricing data with auto select variant.

Input parameters:

- `autoselect_variant` (boolean): To get accurate pricing/buybox data, set this parameter to true.
- `currency`: Currency that will be used to display the prices.
- `domain`: Domain localization for Google.         Use country top level domains.         For example:             - 'co.uk' for United Kingdom             - 'us' for United States             - 'fr' f…
- `geo_location`: The geographical location that the result should be adapted for.         Use ISO-3166 country codes.         Examples:             - 'California, United States'             - 'Mexico'…
- `locale`: Set 'Accept-Language' header value which changes your Google search page web interface language.         Examples:             - 'en-US' for English, United States             - 'de-AT' for…
- `output_format`: The format of the output. Works only when parse parameter is false.             - links - Most efficient when the goal is navigation or finding specific URLs. Use this first when you need to…
- `parse` (boolean): Should result be parsed. If the result is not parsed, the output_format parameter is applied.
- `query` (string, required): Keyword to search for.
- `render`: Whether a headless browser should be used to render the page.         For example:             - 'html' when browser is required to render the page.
- `user_agent_type`: Device type and browser that will be used to determine User-Agent header value.

Output parameters:

- `result` (string)

## Diagnostics

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

## Score history

- 2026-09-20: 75
- 2026-09-19: 75
- 2026-09-18: 75
- 2026-09-17: 75
- 2026-09-16: 75
- 2026-09-15: 75
- 2026-09-14: 75
- 2026-09-13: 75
- 2026-09-12: 75
- 2026-09-11: 75
- 2026-09-10: 75
- 2026-09-09: 74
- 2026-09-08: 74
- 2026-09-07: 73
- 2026-09-06: 73
- 2026-09-05: 72
- 2026-09-04: 72
- 2026-09-03: 71
- 2026-09-02: 71
- 2026-09-01: 70
- 2026-08-31: 70
- 2026-08-30: 69
- 2026-08-29: 69
- 2026-08-28: 69
- 2026-08-27: 68
- 2026-08-26: 68
- 2026-08-25: 66
- 2026-08-24: 65
- 2026-08-23: 65
- 2026-08-22: 64

## Common questions

### What is the io.oxylabs/oxylabs-mcp server?

io.oxylabs/oxylabs-mcp is listed in the public MCP registry as io.oxylabs/oxylabs-mcp. Fetch and process content from specified URLs & sources using the Oxylabs Web Scraper API. This page covers its hosted endpoint (https://mcp.oxylabs.io/mcp).

### Is the io.oxylabs/oxylabs-mcp server safe to use?

io.oxylabs/oxylabs-mcp scores 75 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 io.oxylabs/oxylabs-mcp server expose?

io.oxylabs/oxylabs-mcp exposes 10 tools: ai_crawler, ai_scraper, ai_browser_agent, ai_search, generate_schema, and 5 more. Their descriptions and schemas cost roughly 2,975 tokens of context every time the server is loaded.

### Does the io.oxylabs/oxylabs-mcp server require authentication?

No. We connected to io.oxylabs/oxylabs-mcp without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the io.oxylabs/oxylabs-mcp server still maintained?

io.oxylabs/oxylabs-mcp 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://mcp.oxylabs.io/mcp
- Repository: https://github.com/oxylabs/oxylabs-mcp
- Website: https://oxylabs.io/
- Changelog RSS feed: https://verifymcp.io/servers/io-oxylabs-oxylabs-mcp/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-oxylabs-oxylabs-mcp/mcp.json
- HTML version of this page: https://verifymcp.io/servers/io-oxylabs-oxylabs-mcp/mcp