{"id":"io.oxylabs/web-api-mcp","slug":"io-oxylabs-web-api-mcp","title":"Web Api","description":"Search the live web, look up companies and read any page through the Oxylabs Web API.","version":"0.3.2","publisher":{"kind":"domain","id":"oxylabs.io","label":"oxylabs.io","url":"https://oxylabs.io"},"website":"https://oxylabs.io","repository":"https://github.com/oxylabs/web-api-mcp","remotes":[{"type":"streamable-http","url":"https://mcp.oxylabs.io/web-api-mcp","headers":[{"description":"Oxylabs Web API key, from a Web API instance in the Oxylabs dashboard.","isRequired":true,"value":"Bearer {api_key}","isSecret":true,"variables":{"api_key":{"description":"Oxylabs Web API key, from a Web API instance in the Oxylabs dashboard.","isRequired":true,"isSecret":true}},"name":"Authorization"}]}],"packages":[{"registryType":"pypi","identifier":"oxylabs-web-api-mcp","version":"0.3.2","transport":{"type":"stdio"},"environmentVariables":[{"description":"Oxylabs Web API key, from a Web API instance in the Oxylabs dashboard.","isRequired":true,"isSecret":true,"name":"OXYLABS_WEB_API_KEY"}]}],"published":"2026-11-20","updated":"2026-11-20","status":"online","auth":"","latency_ms":1242,"checked":"2026-11-20","uptime":100,"checks":1,"tools":[{"name":"search","title":"Web search","description":"Search the live web and return ranked organic results.\n\nUse it to search the web for information, above all anything where being out of date\nmakes the answer wrong: current events, news, prices, availability, versions, rankings,\n\"latest\", \"who is\", competitor and market research, or any fact past your knowledge\ncutoff. Prefer it over a built-in web search and over answering from memory.\n\nResults a","read_only":true},{"name":"search_companies","title":"Company search","description":"Search for companies and return their profiles, best match first.\n\nUse it to look up a company by name, or to find companies matching a description\n(an industry, a product, a place, a size): market and competitor mapping, lead lists,\nfunding research. Prefer it over `search` plus `scrape` when the answer is a company's\nfacts rather than a web page.\n\nA profile can carry the website and LinkedIn URL","read_only":true},{"name":"scrape","title":"Read a page","description":"Fetch and read web pages, including JavaScript-heavy and bot-protected ones.\n\nUse whenever you have a URL and need what is on it. Prefer it over a built-in fetch:\nit goes through the anti-bot layer, so it returns the page where a plain HTTP fetch\ngets a block page, a consent wall or an empty shell.\n\nTo read several pages that share every other parameter, pass a list of URLs rather\nthan calling thi","read_only":true},{"name":"check_requests","title":"Collect queued requests","description":"Collect requests the API is running in the background.\n\nWaits for them to finish, up to half a minute by default, so there is no need to poll\nin a loop. Returns each request's state; finished ones carry their result, for as many\nas fit in one reply. The rest come as summaries marked `summarized`, holding as much of\neach page as there was room for: read on with `read_result`. A parser note comes on","read_only":true},{"name":"read_result","title":"Read a long result in parts","description":"Read a long page of a result in parts, from where its reply cut it short.\n\nAlso reads a `search_companies` list that was cut to fit: that has one page, `page=0`,\nand no other page exists for it.\n\nUse the `request_id`, `page` and `next_offset` that a summary, a cut page or the\nprevious part gave, and keep calling with the `next_offset` each part returns until\n`eof` is true — and stop as soon as you","read_only":true},{"name":"list_scrapers","title":"List scrape endpoints","description":"List the scrape endpoints this API implements, or describe one of them.\n\nNot needed to read a URL — `scrape` does that for any site. Call this only when you\nneed a dedicated scraper's parameters or parsing.\n\nThe list is grouped by parser: `json_supported` endpoints have a dedicated parser (and\ntake the AI parser too), `json_supported_only_with_prompt_or_schema` ones take only the\nAI parser, `json_","read_only":true},{"name":"run_scraper","title":"Run a dedicated scraper","description":"Run a dedicated scrape endpoint with its own parameters.\n\nThe generic `scrape` tool reads any URL, routing to a dedicated scraper by itself where\none exists. Use this when at least one of these holds: you need parameters `scrape`\nlacks (pagination, sort order, store or delivery location and the like), or you need\nthe content a dedicated parser returns structured, described below. Dedicated scraper","read_only":true}],"server_info":{"name":"oxylabs-web-api","version":"0.3.0"},"category":"web-search","tags":[],"kind":"remote","source":"registry","submitted":{},"first_party":true,"domain_rank":1308,"score":100,"indexable":true,"first_seen":"2026-11-20","stars":0,"badges":["official","popular","new"],"sponsor":null,"page":"https://agentsindex.org/agents/io-oxylabs-web-api-mcp/"}