Atlas / MCP servers / scrapegraphai / ScrapeGraph

ScrapeGraphSAFE

mcp/scrapegraphai/scrapegraph

ScapeGraph MCP Server

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
13 6r · 6w · 1d
Transport
stdio · streamable-http
License
MIT
Stars
115
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://opensource.org/licenses/MIT) [](https://www.python.org/downloads/) [](https://smithery.ai/server/@ScrapeGraphAI/scrapegraph-mcp)

A production-ready Model Context Protocol (MCP) server that provides seamless integration with the ScrapeGraph AI API. This server enables language models to leverage advanced AI-powered web scraping capabilities with enterprise-grade reliability.

Table of Contents

  • Key Features
  • Quick Start
  • Available Tools
  • Setup Instructions
  • Remote Server Usage
  • Local Usage
  • Google ADK Integration
  • Example Use Cases
  • Error Handling
  • Common Issues
  • Development
  • Contributing
  • Documentation
  • Technology Stack
  • License

API v2

This MCP server targets ScrapeGraph API v2 (https://v2-api.scrapegraphai.com/api), aligned 1:1 with scrapegraph-py PR #84. Auth uses the SGAI-APIKEY header. Environment variables mirror the Python SDK:

  • `SGAI_API_URL` — override the base URL (default https://v2-api.scrapegraphai.com/api)
  • `SGAI_TIMEOUT` — request timeout in seconds (default 120)
  • `SGAI_API_KEY` — API key (can also be passed via MCP scrapegraphApiKey or X-API-Key header)
Legacy aliases (still honored): SCRAPEGRAPH_API_BASE_URL for SGAI_API_URL, `SG
Read from source at commit f19f44e27ec3OBSERVED · 2026-10-07
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code (pypi)
claude mcp add scrapegraph-mcp --env SGAI_API_KEY=${SGAI_API_KEY} -- None scrapegraph-mcp==3.0.0
03

Exposed tools (13)

6 read · 6 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.

ToolRiskDescription
crawl_get_statusread
crawl_resumewriteResume a stopped crawl job (API v2 POST /crawl/:id/resume).
crawl_startwrite
crawl_stopwriteStop a running crawl job (API v2 POST /crawl/:id/stop).
creditsreadReturn remaining API credits (API v2 GET /credits).
historyread
monitor_activitywritePoll per-run tick history for a monitor (API v2 GET /monitor/:id/activity).
monitor_deletedestructiveDelete a monitor (API v2 DELETE /monitor/:id).
monitor_getreadGet one monitor by id (API v2 GET /monitor/:id).
monitor_listreadList monitors (API v2 GET /monitor).
monitor_pausewritePause a monitor (API v2 POST /monitor/:id/pause).
monitor_resumewriteResume a paused monitor (API v2 POST /monitor/:id/resume).
scraperead
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfaceWARN
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (1 observation(s))
Network
declared (3 observation(s))
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (1)

MEDIUMFilesystem / path · mcp.destructive_tools · CWE-22, CWE-59
monitor_delete
Why it matters. 1 tool(s) can delete or overwrite
Fix. prefer a read-only mode or scoped tokens; the page states the blast radius

Gates applied: no_behavioural_pass.

Audited 2026-10-07 · audit v0.4.1 · source sha f19f44e27ec3full audit observations/trust-audit/mcp-server/scrapegraphai__scrapegraph.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-07f19f44e27ec3SAFEB89first audit
06

Questions

What is the ScrapeGraph MCP server?

ScapeGraph MCP Server

What tools does ScrapeGraph expose?

13 in total: 6 read-only, 6 that write, and 1 that can delete or overwrite (monitor_delete). Every one is listed on this page with its risk.

Is ScrapeGraph safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.

What credentials does ScrapeGraph need?

It reads SGAI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does ScrapeGraph run?

It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as scrapegraph-mcp.

How current is this page?

The grade is for one exact copy of the source (f19f44e27ec3), read on 2026-10-07. The repository is watched and re-audited when it changes.

Advertisement