Is ScrapeGraph MCP server safe?

What ScrapeGraph MCP server does

ScrapeGraph MCP Server connects language models to the ScrapeGraph AI API for scraping pages to Markdown and other formats, structured extraction, web search, multi-page crawls and scheduled monitors. It is published in the ScrapeGraphAI/scrapegraph-mcp repository. It sends URLs and prompts to ScrapeGraph's API using SGAI_API_KEY; the API base URL can be overridden with SGAI_API_URL. Before installing, review the v3 tool renames and removals (markdownify, for example, was replaced by scrape), and pay attention to monitor_create, which sets up scheduled jobs on the service that run until you pause or delete them.

Low risk - review the findings before installing

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

Server bound to all network interfaces
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.

ScrapeGraph MCP server is an MCP server analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators, though 1 risky construct is reported for review. It can: mcp tools detected and network egress — capabilities are what the code can do, not a verdict on intent. Risk score 10/100 (low).

scrapegraph-mcp 3.0.0

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

LOW

/ 100 risk score

Snapshot · scanned Nov 13, 2026 · scrapegraph-mcp@3.0.0 · 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 ScrapeGraph 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

Network exposure

Interaction & Communication

Findings (3)

MEDIUMServer bound to all network interfacesST-EXPOSE-BIND

A server is bound to all network interfaces (0.0.0.0), not just your own machine.

src/scrapegraph_mcp/server.py:2093

host = os.getenv("HOST", "0.0.0.0")

Why it matters: Without authentication, other hosts on the network can reach it.

Fix: Bind to 127.0.0.1 for local-only use, or require authentication and restrict access if remote exposure is intended.

CapabilityPython network egressnot scored · severity mediumST-NET-PY

The component makes outbound network requests.

src/scrapegraph_mcp/server.py:80

import httpx

src/scrapegraph_mcp/server.py:226

self.client = httpx.Client(timeout=httpx.Timeout(_api_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/scrapegraph_mcp/server.py:619

mcp = FastMCP("ScapeGraph API MCP Server")

src/scrapegraph_mcp/server.py:1439

@mcp.tool(annotations={"readOnlyHint": True, "destructiveHint": False, "idempotentHint": True})

src/scrapegraph_mcp/server.py:1520

@mcp.tool(annotations={"readOnlyHint": True, "destructiveHint": False, "idempotentHint": False})

src/scrapegraph_mcp/server.py:1615

@mcp.tool(annotations={"readOnlyHint": False, "destructiveHint": False, "idempotentHint": False})

src/scrapegraph_mcp/server.py:1700

@mcp.tool(annotations={"readOnlyHint": True, "destructiveHint": False, "idempotentHint": True})

src/scrapegraph_mcp/server.py:1728

@mcp.tool(annotations={"readOnlyHint": False, "destructiveHint": False, "idempotentHint": False})

src/scrapegraph_mcp/server.py:1739

@mcp.tool(annotations={"readOnlyHint": False, "destructiveHint": False, "idempotentHint": False})

src/scrapegraph_mcp/server.py:1750

@mcp.tool(annotations={"readOnlyHint": True, "destructiveHint": False, "idempotentHint": True})

src/scrapegraph_mcp/server.py:1761

@mcp.tool(annotations={"readOnlyHint": True, "destructiveHint": False, "idempotentHint": False})

src/scrapegraph_mcp/server.py:1798

@mcp.tool(annotations={"readOnlyHint": False, "destructiveHint": False, "idempotentHint": False})

src/scrapegraph_mcp/server.py:1882

@mcp.tool(annotations={"readOnlyHint": True, "destructiveHint": False, "idempotentHint": False})

src/scrapegraph_mcp/server.py:1929

@mcp.tool(annotations={"readOnlyHint": True, "destructiveHint": False, "idempotentHint": True})

src/scrapegraph_mcp/server.py:1940

@mcp.tool(annotations={"readOnlyHint": True, "destructiveHint": False, "idempotentHint": True})

src/scrapegraph_mcp/server.py:1951

@mcp.tool(annotations={"readOnlyHint": False, "destructiveHint": False, "idempotentHint": False})

src/scrapegraph_mcp/server.py:1962

@mcp.tool(annotations={"readOnlyHint": False, "destructiveHint": False, "idempotentHint": False})

src/scrapegraph_mcp/server.py:1973

@mcp.tool(annotations={"readOnlyHint": False, "destructiveHint": True, "idempotentHint": False})

src/scrapegraph_mcp/server.py:1984

@mcp.tool(annotations={"readOnlyHint": True, "destructiveHint": False, "idempotentHint": True})

src/scrapegraph_mcp/server.py:2011

@mcp.tool(annotations={"readOnlyHint": True, "destructiveHint": False, "idempotentHint": True})

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

Fix: Review the declared MCP tools and their permissions.

Maintain ScrapeGraph 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 →