Is Oxylabs MCP server safe?

What Oxylabs MCP server does

The Oxylabs MCP server lets AI models scrape URLs, render JavaScript-heavy pages, run Google and Amazon scrapers, crawl and map sites, drive a browser agent and reach geo-targeted web data. It is published in the oxylabs/oxylabs-mcp repository, on PyPI as oxylabs-mcp, and as a hosted endpoint at mcp.oxylabs.io. It sends requests to Oxylabs services using OXYLABS_USERNAME and OXYLABS_PASSWORD for the Web Scraper API and/or OXYLABS_AI_STUDIO_API_KEY for AI Studio; which tools appear depends on the credentials provided. Before installing, supply only the credential set for the tools you actually need.

No malicious indicators - review capabilities before installing

Notable — review in context (a capability is not a malicious indicator):

Python network egress
MCP tool surface detected

What to do: Nothing here argues against installing it. Grant the capabilities it lists only if you expect the tool to need them.

Oxylabs MCP server is an MCP server analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators. It can: mcp tools detected and network egress — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).

oxylabs-mcp 0.10.2

GitHub repository, read as a PyPI package · https://github.com/oxylabs/oxylabs-mcp

LOW

/ 100 risk score

Snapshot · scanned Nov 13, 2026 · oxylabs-mcp@0.10.2 · engine 1.1.0 / ruleset 100

Get notified when this component changes

Change alerts aren't live yet. Leave your email and we'll let you know when they launch. We use it only for this and delete it on request.

Automated static-analysis result. It can contain false positives and false negatives, and is not a claim about the intent of Oxylabs MCP server's authors. Report a false positive.

Capabilities — what this component can do (not a risk score):

mcp tools detectednetwork egress

Behavioral traits

How this component maps to the CSA agentic threat model. Descriptive — it never affects the risk score.

Tool surface

Tool Usage

Network egress

Interaction & Communication / Direct Communication

Findings (2)

CapabilityPython network egressnot scored · severity mediumST-NET-PY

The component makes outbound network requests.

src/oxylabs_mcp/utils.py:14-20

from httpx import (
    AsyncClient,
    BasicAuth,
    HTTPStatusError,
    RequestError,
    Timeout,
)

src/oxylabs_mcp/utils.py:339

auth = BasicAuth(username=username, password=password)

src/oxylabs_mcp/utils.py:341-346

async with AsyncClient(
        timeout=Timeout(settings.OXYLABS_REQUEST_TIMEOUT_S),
        verify=True,
        headers=headers,
        auth=auth,
    ) as client:

src/oxylabs_mcp/utils.py:342

timeout=Timeout(settings.OXYLABS_REQUEST_TIMEOUT_S),

Why it matters: Usually legitimate, but confirm the destinations are expected and no sensitive data leaves.

Fix: Confirm the destination hosts are expected and that no sensitive data is sent off-host.

CapabilityMCP tool surface detectednot scored · severity lowST-MCP-DETECTED

An MCP tool surface (manifest or tool definitions) was found.

server.json:1

src/oxylabs_mcp/__init__.py:12

mcp = FastMCP("oxylabs_mcp", version=version("oxylabs-mcp"))

src/oxylabs_mcp/tools/ai_studio.py:32

mcp = FastMCP("ai_studio")

src/oxylabs_mcp/tools/ai_studio.py:35

@mcp.tool(annotations=ToolAnnotations(readOnlyHint=True))

src/oxylabs_mcp/tools/ai_studio.py:107

@mcp.tool(annotations=ToolAnnotations(readOnlyHint=True))

src/oxylabs_mcp/tools/ai_studio.py:166

@mcp.tool(annotations=ToolAnnotations(readOnlyHint=True))

src/oxylabs_mcp/tools/ai_studio.py:219

@mcp.tool(annotations=ToolAnnotations(readOnlyHint=True))

src/oxylabs_mcp/tools/ai_studio.py:264

@mcp.tool(annotations=ToolAnnotations(readOnlyHint=True))

src/oxylabs_mcp/tools/ai_studio.py:285

@mcp.tool(annotations=ToolAnnotations(readOnlyHint=True))

src/oxylabs_mcp/tools/scraper.py:21

mcp = FastMCP("scraper")

src/oxylabs_mcp/tools/scraper.py:24

@mcp.tool(annotations=ToolAnnotations(readOnlyHint=True))

src/oxylabs_mcp/tools/scraper.py:55

@mcp.tool(annotations=ToolAnnotations(readOnlyHint=True))

src/oxylabs_mcp/tools/scraper.py:110

@mcp.tool(annotations=ToolAnnotations(readOnlyHint=True))

src/oxylabs_mcp/tools/scraper.py:170

@mcp.tool(annotations=ToolAnnotations(readOnlyHint=True))

Why it matters: Just context — review which tools it offers and their permissions.

Fix: Review the declared MCP tools and their permissions.

Maintain Oxylabs MCP server?

Check the next package before your agent installs it

The free Claude Code plugin scans each npm, PyPI or MCP package with this report's open-source engine before the install command runs. It runs on your machine and needs no account.

Set up the plugin Or scan pull requests in CI with the GitHub Action

Check your own component

Run the same evidence-backed scan on any MCP server, agent skill, or package.

Scan your own component

How we determine this: deterministic static analysis (regex + AST), evidence-anchored, no code execution. Methodology →