Is Scrapegraph MCP server safe?

scrapegraph-mcp is an AI python_package analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators, though 3 risky constructs are 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

python_package · https://github.com/ScrapeGraphAI/scrapegraph-mcp

LOW

/ 100 malicious-risk

Snapshot · scanned Jun 20, 2026 · scrapegraph-mcp@3.0.0 · engine 0.18.0 / ruleset 19

No malicious indicators - review capabilities before installing

Notable — review in context (capabilities are not malware):

Python network egress
Server bound to all network interfaces
MCP tool surface detected

No malicious indicators found by static analysis.

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

mcp tools detectednetwork egress

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:2040-2040

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.

MEDIUMPython network egressST-NET-PY

The component makes outbound network requests.

src/scrapegraph_mcp/server.py:80-80

import httpx

src/scrapegraph_mcp/server.py:183-183

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.

LOWMCP tool surface detectedST-MCP-DETECTED

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

server.json:1-1

.agent/system/mcp_protocol.md:103-103

mcp = FastMCP("ScapeGraph API MCP Server")

.agent/system/mcp_protocol.md:106-106

@mcp.tool()

.agent/system/mcp_protocol.md:239-239

@mcp.tool()

.agent/system/mcp_protocol.md:282-282

@mcp.tool()

.agent/system/mcp_protocol.md:327-327

@mcp.tool()

.agent/system/mcp_protocol.md:620-620

@mcp.tool()

.agent/system/project_architecture.md:92-92

- MCP tool definitions (`@mcp.tool()` decorators)

.agent/system/project_architecture.md:149-149

- Created with `FastMCP("ScapeGraph API MCP Server")`

.agent/system/project_architecture.md:150-150

- Exposes tools via `@mcp.tool()` decorators

.agent/system/project_architecture.md:160-160

5. Define MCP tools with `@mcp.tool()` decorators

.agent/system/project_architecture.md:171-171

- `@mcp.tool()` decorators expose functions as MCP tools

.agent/system/project_architecture.md:189-189

The server exposes many `@mcp.tool()` handlers (see repository `README.md` for the full table). The detailed subsections below still use **v1-style endpoint names** in several places; treat them as illustrative and prefer the v2 mapping in …

.agent/system/project_architecture.md:760-760

@mcp.tool()

src/scrapegraph_mcp/server.py:576-576

mcp = FastMCP("ScapeGraph API MCP Server")

src/scrapegraph_mcp/server.py:1386-1386

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

src/scrapegraph_mcp/server.py:1467-1467

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

src/scrapegraph_mcp/server.py:1562-1562

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

src/scrapegraph_mcp/server.py:1647-1647

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

src/scrapegraph_mcp/server.py:1675-1675

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

src/scrapegraph_mcp/server.py:1686-1686

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

src/scrapegraph_mcp/server.py:1697-1697

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

src/scrapegraph_mcp/server.py:1708-1708

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

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

Fix: Review the declared MCP tools and their permissions.

Check your own component

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

Scan your own component

Or get notified if this component's risk changes:

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