Browser Tools
oassis.dev
A browser automation and web scraping server that opens sessions, performs actions, and extracts page data in multiple formats.
ENDPOINT 1
https://api.oassis.dev/mcp
MCP server metadata
- Name
- oassis
- Version
- 1.0.1
Web extraction and browser control for agents. You can try it with no key and no account: 10 page or document reads a day, 10 site listings a day, and — once, ever — one browser session with 10 actions and 5 searches. Crawls, batches and AI extraction need a key. Call GET /mcp for the table. After that, send an API key in `Authorization: Bearer oas_…`, or pay per call with a wallet over the HTTP API (x402, USDC on Base) with no account at all. To read a page use web_scrape; to fill in or click something, open a session with web_session_open and act with web_act; to find urls use web_map before paying to read them.
Known tools 11
web_scrapeProcesses a page and returns every output you ask for at once: markdown, html, links, screenshot, PDF, accessibility tree, elements by selector, AI-structured data, and `controls` (what can be clicked).
Inferred read-onlyweb_session_openOpens a browser on a page and leaves it open, returning the map of controls.
Inferred read-onlyweb_scrape_batchA batch OF SCRAPES: reads a list of urls YOU give it (2 to 50, from any sites) and returns a jobId.
Inferred read-onlyweb_batch_statusChecks a batch of scrapes: status, how many are done, and the results.
Inferred read-onlyweb_mapEvery url of a site, fast and cheap: its sitemap plus, optionally, the links on the page.
Inferred read-onlyweb_crawl_statusChecks a crawl: status, pages read, discovered and still queued, and the pages themselves.
Inferred read-onlyweb_search_exaSearch the web with Exa's index: a query instead of a url, for when you do not know where to look.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.oassis]
url = "https://api.oassis.dev/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"oassis": {
"type": "http",
"url": "https://api.oassis.dev/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: oassis
Remote MCP URL: https://api.oassis.dev/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"oassis": {
"url": "https://api.oassis.dev/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"oassis": {
"type": "http",
"url": "https://api.oassis.dev/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "oassis",
"transport": "streamable-http",
"url": "https://api.oassis.dev/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
ENDPOINT 2
https://oassis.dev/mcp
MCP server metadata
- Name
- oassis
- Version
- 1.0.1
Web extraction and browser control for agents. You can try it with no key and no account: 10 page or document reads a day, 10 site listings a day, and — once, ever — one browser session with 10 actions and 5 searches. Crawls, batches and AI extraction need a key. Call GET /mcp for the table. After that, send an API key in `Authorization: Bearer oas_…`, or pay per call with a wallet over the HTTP API (x402, USDC on Base) with no account at all. To read a page use web_scrape; to fill in or click something, open a session with web_session_open and act with web_act; to find urls use web_map before paying to read them.
Known tools 11
web_scrapeProcesses a page and returns every output you ask for at once: markdown, html, links, screenshot, PDF, accessibility tree, elements by selector, AI-structured data, and `controls` (what can be clicked).
Inferred read-onlyweb_session_openOpens a browser on a page and leaves it open, returning the map of controls.
Inferred read-onlyweb_scrape_batchA batch OF SCRAPES: reads a list of urls YOU give it (2 to 50, from any sites) and returns a jobId.
Inferred read-onlyweb_batch_statusChecks a batch of scrapes: status, how many are done, and the results.
Inferred read-onlyweb_mapEvery url of a site, fast and cheap: its sitemap plus, optionally, the links on the page.
Inferred read-onlyweb_crawl_statusChecks a crawl: status, pages read, discovered and still queued, and the pages themselves.
Inferred read-onlyweb_search_exaSearch the web with Exa's index: a query instead of a url, for when you do not know where to look.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.oassis]
url = "https://oassis.dev/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"oassis": {
"type": "http",
"url": "https://oassis.dev/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: oassis
Remote MCP URL: https://oassis.dev/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"oassis": {
"url": "https://oassis.dev/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"oassis": {
"type": "http",
"url": "https://oassis.dev/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "oassis",
"transport": "streamable-http",
"url": "https://oassis.dev/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for oassis.dev was fetched 2026-10-03T07:44:00.308Z.
oassis.dev is assessed as Neutral: No suspicious signals found, but no strong positive signal either
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.