Web API MCP

● Active

io.oxylabs/web-api-mcp

Search the live web, look up companies and read any page through the Oxylabs Web API.

Connect this server

One click to install, or copy the config below. Suits: Claude Desktop · Cursor.

Add to Cursor Add to VS CodeClaude Desktop / Claude Code: paste the config below.

Or add it manually — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor):

{
  "mcpServers": {
    "web-api-mcp": {
      "command": "uvx",
      "args": [
        "oxylabs-web-api-mcp"
      ],
      "env": {
        "OXYLABS_WEB_API_KEY": "<your OXYLABS_WEB_API_KEY>"
      }
    }
  }
}
One line, from the terminal
Claude Code
claude mcp add --env OXYLABS_WEB_API_KEY='<your OXYLABS_WEB_API_KEY>' --transport stdio web-api-mcp -- uvx oxylabs-web-api-mcp
OpenAI Codex CLI
codex mcp add web-api-mcp --env OXYLABS_WEB_API_KEY='<your OXYLABS_WEB_API_KEY>' -- uvx oxylabs-web-api-mcp
VS Code
code --add-mcp '{"name":"web-api-mcp","type":"stdio","command":"uvx","args":["oxylabs-web-api-mcp"],"env":{"OXYLABS_WEB_API_KEY":"<your OXYLABS_WEB_API_KEY>"}}'

Syntax from each client's docs (Claude Code: claude mcp add; Codex: codex mcp add; VS Code: code --add-mcp). Placeholders in angle brackets are values you fill in.

Environment variables
  • OXYLABS_WEB_API_KEYrequiredsecretOxylabs Web API key, from a Web API instance in the Oxylabs dashboard.

A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.

Category
Search & Web
Version
0.3.2
Registry
active
Published
11/20/2026
Listed in:Official MCP registry ↗how this is checked

Is it safe? Is it maintained?

Serverdex check: Nov 22, 2026

Looks healthy: Web API MCP is maintained, open source, hosted endpoint answering without a key.

Maintained
Active
Last commit 2 days ago (Nov 20, 2026), 0 open issues.
Official registry
Active
Published as io.oxylabs/web-api-mcp in the official MCP registry, version 0.3.2.
Source
Open source, MIT
Public repository under the MIT licence, 71 stars, 11 forks.
Runs
Local package or hosted
Ships as a local package (PyPI) that runs on your machine, and as a hosted endpoint at mcp.oxylabs.io that receives what your client sends it.
Credentials
None needed to connect
The hosted endpoint completed the Serverdex initialize + tools/list handshake with no key (checked Nov 22, 2026); individual tools may still ask for one.
Owner
Unclaimed
Nobody has claimed this page yet; the data above comes from the registry, GitHub and the live check.

Facts only: last commit and licence from GitHub, the entry's status from the official registry, credentials from the live check. Not a code audit — run the security scan on the endpoint yourself and see the status history.

Live check

checked Nov 22, 2026, 07:07 UTCStatus history & uptime →
● Working534 msprotocol 2025-06-18v0.3.0promptsresourcestools

The endpoint answered the MCP handshake as "oxylabs-web-api" and listed 7 tools. Answering since Nov 21, 2026.

Context cost ≈ 4.1k tokens of tool definitions a client loads per conversation (estimate: characters ÷ 4) across 7 tools.

Tools (7)

  • search3 params

    Search the live web and return ranked organic results. Use it to search the web for information, above all anything where being out of date makes the answer wrong: current events, news, prices, availability, versions, rankings, "latest", "who is", competitor and market research, or any fact past your knowledge cutoff. Prefer it over a built-in web search and over answering from memory. Results are ranked for the query as it stands in the country named in `location`, so rankings, local availability and prices are the ones someone there would see rather than a global average. Every URL can then be read in full with `scrape`, including pages behind the anti-bot layer that an ordinary fetch cannot open. Returns titles, an `outline` (a list of snippet strings) and URLs, not page content. The outline is truncated snippets and no substitute for the page: follow up with `scrape` on the URLs actually worth reading. Not for local files, git, or anything off the public web.

    Show parameters
    • querystringrequiredWhat to search for, as a natural search phrase. Keyword-shaped queries beat sentence-shaped ones. One question per search.
    • max_resultsintegerMaximum number of results to return. The response may contain fewer.
    • locationISO 3166-1 alpha-2 country code to rank results for. Pass it whenever the answer is geographic. A place name such as "Germany" is rejected.
  • search_companies2 params

    Search for companies and return their profiles, best match first. Use it to look up a company by name, or to find companies matching a description (an industry, a product, a place, a size): market and competitor mapping, lead lists, funding research. Prefer it over `search` plus `scrape` when the answer is a company's facts rather than a web page. A profile can carry the website and LinkedIn URLs, description, industry, founding year, employee count, headquarters, funding, annual revenue and web traffic; any field may be missing. The figures are often estimates and not necessarily current: check one that matters on the company's own website with `scrape`. There are no location or filter parameters: describe the whole set you want in one `query`.

    Show parameters
    • querystringrequiredA company name or a free-text description of the companies wanted. Say what they do, where and how big, in words.
    • max_resultsintegerMaximum number of companies to return. Profiles are long: ask for what you will use. The response may contain fewer.
  • scrape7 params

    Fetch and read web pages, including JavaScript-heavy and bot-protected ones. Use whenever you have a URL and need what is on it. Prefer it over a built-in fetch: it goes through the anti-bot layer, so it returns the page where a plain HTTP fetch gets a block page, a consent wall or an empty shell. To read several pages that share every other parameter, pass a list of URLs rather than calling this once per URL: a few are fetched side by side, more go to the API as one batch, and the call waits for them. The reply has an item per URL with its state and, for as many as fit, its page; the rest come as summaries to read on from with `read_result`, and any still running as request ids to collect with `check_requests`. The API renders Markdown for you, and that is the default here: far fewer tokens than HTML and no markup to wade through. Try it without `run_js` first. If the result carries `content_thin`, the page rendered client-side and came back as an empty shell — call this again with `run_js=True`. Rendering is slow; when it outlives the synchronous call the request is queued, and you get a request id to collect with `check_requests` instead of the content. `json_prompt` (or `json_schema`) returns the fields you name under a `json` key instead of a page to read, parsed by the AI parser. When you need parameters this tool lacks (pagination, sort order, store or delivery location and the like), or the content a dedicated parser returns structured — results, products, sellers, hotels, questions and answers and the like — `run_scraper` on the site's dedicated scraper is the better fit, where the site has one. Very large pages are not returned whole. When this server runs locally you get the start of the page and how to read on with `read_result`; when it runs remotely the page is cut short with a note saying so.

    Show parameters
    • urlrequiredAbsolute http(s) URL of the page to read, or a list of URLs to read several pages that share every other parameter in one call.
    • formatstringmarkdown to read the page — far fewer tokens, structure intact. html only when you need the markup itself: attributes, embedded JSON-LD. screenshot for a PNG of
    • locationTwo-letter country code to fetch the page from. Use it when the page varies by country — pricing, availability, language.
    • deviceViewport to fetch as. The API's default is desktop.
    • run_jsbooleanExecute the page's JavaScript. Needed for pages that render client-side and arrive empty otherwise. Slow: if the render outlives the synchronous call it is queu
    • json_promptFields to pull out as JSON, in plain words: name them and say what shape you want. Used by the AI parser, which runs when the endpoint has no dedicated parser o
    • json_schemaA JSON Schema the AI parser's output must follow, instead of `json_prompt`: the two cannot be combined. Use it when you need the exact same shape off many pages
  • check_requests1 param

    Collect requests the API is running in the background. Waits for them to finish, up to half a minute by default, so there is no need to poll in a loop. Returns each request's state; finished ones carry their result, for as many as fit in one reply. The rest come as summaries marked `summarized`, holding as much of each page as there was room for: read on with `read_result`. A parser note comes once, in `parser_notes`, and each result names its own. Only the first few screenshots come back as images. If some are still pending, call again with only their request ids.

    Show parameters
    • request_idsarrayrequiredThe `request_id`s of queued requests, from `scrape` or `run_scraper` replies or an earlier call to this tool. A single id is fine.
  • read_result4 params

    Read a long page of a result in parts, from where its reply cut it short. Also reads a `search_companies` list that was cut to fit: that has one page, `page=0`, and no other page exists for it. Use the `request_id`, `page` and `next_offset` that a summary, a cut page or the previous part gave, and keep calling with the `next_offset` each part returns until `eof` is true — and stop as soon as you have what you need rather than reading the whole page by reflex. Reading runs no new scrape: the page comes from disk where this server wrote it, or from the API, which keeps the results of queued requests. Returns `text` plus `offset`, `returned_chars`, `total_chars`, `next_offset` and `eof`.

    Show parameters
    • request_idstringrequiredThe `request_id` of the result to read.
    • pageintegerWhich page of the result, counting from 0. Most results have one; a request for several pages of results, a search say, has more. A `search_companies` list is a
    • offsetintegerCharacter to start at: the `next_offset` a summary, a cut page or the previous part gave.
    • lengthintegerMost characters to return; fewer come back if they would not fit.
  • list_scrapers1 param

    List the scrape endpoints this API implements, or describe one of them. Not needed to read a URL — `scrape` does that for any site. Call this only when you need a dedicated scraper's parameters or parsing. The list is grouped by parser: `json_supported` endpoints have a dedicated parser (and take the AI parser too), `json_supported_only_with_prompt_or_schema` ones take only the AI parser, `json_not_supported` ones return no JSON at all. The batch endpoints listed under /v1/async/scrape/batch/ are used for you: give `run_scraper` a list instead. Call this before assuming a dedicated scraper does or does not exist for a site, then call it again with the endpoint name to get the JSON Schema of what that endpoint accepts: types, `required`, `enum` values and defaults. That is the authoritative parameter list — more current than any documentation. Run the endpoint itself with `run_scraper`.

    Show parameters
    • endpointName a scrape endpoint to get the JSON Schema of its request body instead of the list. Omit it to list what exists.
  • run_scraper6 params

    Run a dedicated scrape endpoint with its own parameters. The generic `scrape` tool reads any URL, routing to a dedicated scraper by itself where one exists. Use this when at least one of these holds: you need parameters `scrape` lacks (pagination, sort order, store or delivery location and the like), or you need the content a dedicated parser returns structured, described below. Dedicated scrapers exist only for major sites (big search engines, marketplaces, retailers, video platforms and AI chats); most sites have none. Look the endpoint up with `list_scrapers()`, read its parameters with `list_scrapers(endpoint)`, then call it here. An endpoint with a dedicated parser returns its parsed JSON by default; set `output` in `params` (e.g. ["markdown"]) to read the page instead. Other endpoints return Markdown wherever they offer it, unless `output` says otherwise; for structured data from them, describe the fields in `json_prompt`. Endpoints with a dedicated parser return typical page content in a predefined shape: search results (organic links, ads, images, news, videos, SERP extras), product listings and details (title, price, stock, seller, reviews), seller profiles, bestsellers, hotel offers, AI chat answers (prompt, response, citations), YouTube video and channel metadata. That runs first; with no dedicated parser, or one that failed or returned nothing, the AI parser extracts what `json_prompt` describes. The result's `parser` says which one answered, and `parser_note` carries the dedicated parser's own verdict (e.g. PARSE_PARTIAL_SUCCESS_SOME_FIELDS_DEFAULT). If a dedicated result lacks what you need, call again with `parser="ai"`. To run several URLs or queries with the same parameters, give `url` or `query` in `params` as a list: a few run side by side, more go to the endpoint's batch in one request, and the call waits for them. The reply has an item per URL or query, as `scrape` gives for a list. A batch cannot fall back from the dedicated parser to the AI

    Show parameters
    • endpointstringrequiredA scrape endpoint path from `list_scrapers`, without the /v1/ prefix, e.g. 'scrape/amazon/search'.
    • paramsobjectrequiredThe endpoint's own request body. Get its JSON Schema from `list_scrapers(endpoint)` rather than guessing the keys. Give `url` or `query` as a list to run severa
    • structuredbooleanReturn parsed JSON instead of page content. Implied by `json_prompt` or `json_schema`, and by an endpoint with a dedicated parser unless `output` in `params` as
    • parserstringauto uses the endpoint's dedicated parser when it has one and falls back to the AI parser when that fails or returns nothing. ai goes straight to the AI parser
    • json_promptFields to pull out as JSON, in plain words: name them and say what shape you want. Used by the AI parser, which runs when the endpoint has no dedicated parser o
    • json_schemaA JSON Schema the AI parser's output must follow, instead of `json_prompt`: the two cannot be combined. Use it when you need the exact same shape off many pages

Checked by Serverdex with a plain initialize + tools/list call to mcp.oxylabs.io/web-api-mcp, no credentials, about once a day. A failed check is never a removal.

On GitHub

read Nov 21, 2026
Stars
71
Forks
11
Last push
Nov 20, 2026
License
MIT

Pythonmcpmcp-servermcp-serversmcp-toolsweb-apiweb-api-mcpweb-apis

From the README

Oxylabs Web API — MCP Server This repository is a developer-focused, technical reference covering the official Model Context Protocol server for the Oxylabs Web API. It gives any MCP-capable agent live web access – search, scrape pages as Markdown or JSON, and call dedicated scrapers – through one MCP connection. The tools and their behavior are the same on both options, and the sections on self-hosting cover everything you need to run the server yourself. All seven are annotated readOnlyHint — nothing here writes anything, so clients can run them without prompting. Requirements • An Oxylabs Web API key — in the Oxylabs dashboard, create a Web API instance, open it, and copy the API key shown at the top of the instance page. • For Remote MCP – an MCP client that supports remote (HTTP) MCP servers with custom headers, such as Claude Code, Codex, or Cursor. • For self-hosting – Python 3.10+ (built on FastMCP, installed with the package) and uv. Connect to the Remote MCP server The server is hosted and maintained by Oxylabs. There is nothing to install or update. The server authenticates each request with your Web API key, sent as an Authorization: Bearer header. Set the key as an environment variable in the terminal where you run your client: Claude Code: Codex: Cursor — one click, then make the key visible to Cursor (below): Cursor reads ${env:OXYLABSWEBAPIKEY} from its own environment.…

Read the full README on GitHub →

Remotes

  • streamable-httphttps://mcp.oxylabs.io/web-api-mcp

The most-starred Search & Web servers in the index, with their live-check result.

ServerStarsLast pushLive check
Browser Use121,623Nov 2026Working
Scrapling MCP Server104,822Nov 2026Local / not checked
Chrome DevTools MCP58,028Nov 2026Local / not checked
Chrome DevTools MCP58,014Nov 2026Local / not checked
com.puter MCP Server44,182Nov 2026Needs sign-in

Web API MCP: questions people ask

Is Web API MCP a remote or a local MCP server?
According to its entry in the official MCP registry, Web API MCP ships as a hosted endpoint (streamable-http) that your client connects to by URL and as a local package (PyPI) that your client starts on your machine. Use the hosted endpoint when your client supports Streamable HTTP; use the package when you want it to run locally.
Does Web API MCP need an API key?
Its hosted endpoint completed the Serverdex live check — an MCP initialize + tools/list call — with no credentials on Nov 22, 2026. Individual tools may still ask for a key when called.
Is Web API MCP safe to use?
Looks healthy: Web API MCP is maintained, open source, hosted endpoint answering without a key. In detail — maintained: Active; official registry: Active; source: Open source, MIT; runs: Local package or hosted; credentials: None needed to connect. Serverdex check of Nov 22, 2026. This is a reading of the repository, the registry entry and the live check, not a code audit; run the Serverdex security scan on the endpoint before trusting it with real data.
Is Web API MCP still maintained?
Active: the repository's last commit 2 days ago. Last push Nov 20, 2026, 71 GitHub stars, MIT licence. Read from GitHub on Nov 21, 2026.
What tools does Web API MCP expose?
7 tools as listed by the server itself during the live check, including search, search_companies, scrape, check_requests, read_result. The full list with parameters is in the Live check section above.
How do I add Web API MCP to Claude, Cursor or VS Code?
Copy the config in "Connect this server" into your client's MCP config file (claude_desktop_config.json, ~/.cursor/mcp.json or .vscode/mcp.json), or use the one-click Add to Cursor / Add to VS Code buttons and the one-line commands for Claude Code and Codex; then restart the client.
  1. Oxylabs MCPFetch and process content from specified URLs & sources using the Oxylabs Web Scraper API.★ 106
  2. Oxylabs Oxylabs MCPFetch and process content from specified URLs using the Oxylabs Web Scraper API.★ 106
Browse all Search & Web →

Add the badge to your site

Show visitors that Web API MCP is listed here — it’s also the link we check for a free listing.

Web API MCP — listed on Serverdex

HTML — for your website

<a href="https://serverdex.io/server/io-oxylabs-web-api-mcp?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="Web API MCP — listed on Serverdex" width="123" height="40" loading="lazy"></a>

Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.

Markdown — for your README

[![Web API MCP — listed on Serverdex](https://serverdex.io/brand/badge.svg)](https://serverdex.io/server/io-oxylabs-web-api-mcp?utm_source=badge)

Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.

Add to CursorAdd to VS CodeOpen in Claude Code

Install buttons — for your README

[![Add to Cursor](https://serverdex.io/brand/install-cursor.svg)](https://serverdex.io/install/cursor/io-oxylabs-web-api-mcp) [![Add to VS Code](https://serverdex.io/brand/install-vscode.svg)](https://serverdex.io/install/vscode/io-oxylabs-web-api-mcp) [![Open in Claude Code](https://serverdex.io/brand/install-claude-code.svg)](https://serverdex.io/install/claude-code/io-oxylabs-web-api-mcp)

One click opens Cursor or VS Code with this server's config prefilled; the Claude Code button lands on the one-line command. The links point at Serverdex, so when your config changes the buttons keep working.

Install buttons — HTML for your docs

<a href="https://serverdex.io/install/cursor/io-oxylabs-web-api-mcp"><img src="https://serverdex.io/brand/install-cursor.svg" alt="Add to Cursor — via Serverdex" width="140" height="28"></a>
<a href="https://serverdex.io/install/vscode/io-oxylabs-web-api-mcp"><img src="https://serverdex.io/brand/install-vscode.svg" alt="Add to VS Code — via Serverdex" width="147" height="28"></a>
<a href="https://serverdex.io/install/claude-code/io-oxylabs-web-api-mcp"><img src="https://serverdex.io/brand/install-claude-code.svg" alt="Open in Claude Code — via Serverdex" width="180" height="28"></a>

Same buttons as plain links for a docs page or website.

Prefer a live badge with the score, stars and live check? Score badge (links to a page that explains the number and back to this listing).