MCP server · Audited from source
Scrapling MCP server
by d4vinci/ScraplingBSD-3-Clause licenceAudited 12 Nov 2026 · source ca4abccde6f8
Is it safe? No — BLOCK, grade F (36/100). No tools were found in its source. The audit recorded 49 findings (0 critical, 2 high, 13 medium, 34 low). Maintainer's description: 🕷️ The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev
Cite
Cite this page
ModelsAtlas. “Scrapling MCP server (D4Vinci/Scrapling)”. Retrieved 12 Nov 2026. https://modelsatlas.com/mcp/d4vinci/scrapling
Why this is BLOCK. The audit found 0 critical and 2 high findings; the most severe is Code injection at scrapling/spiders/checkpoint.py:74. Each finding is listed below with its file and line.
Why this page is still public. People search for this server by name. Hiding it would leave them with the README's word alone; here they see what the code does. We list it so you can decide, and we do not show connect commands for BLOCK servers.
Trust audit
Audit 0.4.1 · full source read 12 Nov 2026
49 findings, listed below with the file and line each was found on. Grade A needs a sandboxed behavioural run too; this audit read the source only.
What the source does
- FilesystemDeclared2 observations
- NetworkDeclared16 observations
- ShellDeclared4 observations
- DependenciesNot pinnedSome ranges float
- SecretsNone foundNo keys in source
Findings (49)
Sorted by severity · the 25 most severe of 49 are listed
HIGHCode injectioncode.deserialize · scrapling/spiders/checkpoint.py:74
data: CheckpointData = pickle.loads(content)
- Why
- deserialises untrusted bytes into live objects
- Fix
- use json or yaml.safe_load
HIGHNetwork egressnet.tls_off · scrapling/core/shell.py:179
_parser.add_argument("-k", "--insecure", action="store_true")- Why
- certificate verification is disabled
- Fix
- leave verification on
MEDIUMInventory / provenanceinv.binary · agent-skill/Scrapling-Skill.zip
Scrapling-Skill.zip
- Why
- a compiled or binary member cannot be reviewed from source
- Fix
- ship source, or explain the binary in the README
MEDIUMCode injectioncode.dynamic_import · scrapling/__init__.py:29
module = __import__(module_path, fromlist=[class_name])
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMCode injectioncode.dynamic_import · scrapling/fetchers/__init__.py:38
module = __import__(module_path, fromlist=[class_name])
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMNetwork egressnet.beacon_words · scrapling/core/ai/server.py:841
description="Block font, image, media, beacon, object, imageset, texttrack, websocket, csp_report, and stylesheet requests."
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMNetwork egressnet.beacon_words · scrapling/core/ai/server.py:928
description="Block font, image, media, beacon, object, imageset, texttrack, websocket, csp_report, and stylesheet requests."
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMNetwork egressnet.beacon_words · scrapling/engines/constants.py:6
"beacon",
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMNetwork egressnet.beacon_words · scrapling/engines/toolbelt/ad_domains.py:1048
"beacon.gu-web.net",
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMNetwork egressnet.beacon_words · scrapling/engines/toolbelt/ad_domains.py:1049
"beacon.netflix.com",
- Why
- No further detail recorded for this rule.
- Fix
- —
LOWInventory / provenanceinv.symlink · docs/locales/ar/assets
docs/locales/ar/assets
- Why
- link not followed
- Fix
- —
LOWInventory / provenanceinv.symlink · docs/locales/ar/stylesheets
docs/locales/ar/stylesheets
- Why
- link not followed
- Fix
- —
LOWInventory / provenanceinv.symlink · docs/locales/de/assets
docs/locales/de/assets
- Why
- link not followed
- Fix
- —
LOWInventory / provenanceinv.symlink · docs/locales/de/stylesheets
docs/locales/de/stylesheets
- Why
- link not followed
- Fix
- —
LOWInventory / provenanceinv.symlink · docs/locales/es/assets
docs/locales/es/assets
- Why
- link not followed
- Fix
- —
LOWCode injectioncode.deserialize · tests/spiders/test_checkpoint.py:45
restored = pickle.loads(pickled)
- Why
- deserialises untrusted bytes into live objects
- Fix
- use json or yaml.safe_load
LOWCode injectioncode.deserialize · tests/spiders/test_request.py:329
restored = pickle.loads(pickled)
- Why
- deserialises untrusted bytes into live objects
- Fix
- use json or yaml.safe_load
Tools it exposes
None declared in source
No tools were found in the source, so we cannot say what this server exposes.
Safer alternatives
All web search servers →kehvinbehvin/json-mcp-filter
JSON MCP server to filter only relevant data for your LLM
exa-labs/exa-mcp-server
Exa MCP for web search and web crawling!
just-every/mcp-read-website-fast
Quickly reads webpages and converts to markdown for fast, token efficient web scraping
Audit history
- ✕BLOCK F 36 / 100
First audit ·
ca4abccde6f8
README badge
Badges show the current verdict, BLOCK included
A badge cannot be hidden by the maintainer while the verdict is BLOCK. Fix the findings, push, and the re-audit updates it.
Questions about Scrapling MCP server
What is the Scrapling MCP server?
Is Scrapling safe to connect to an agent?
What credentials does Scrapling need?
How does Scrapling run?
How current is this page?
I already installed Scrapling. What should I do?
Can the verdict change?
Sources
- D4Vinci/Scrapling on GitHub — the source we read, its licence, stars and activityObserved · 12 Nov 2026
- ModelsAtlas trust audit — BLOCK verdict for commit ca4abccde6f8Observed · 12 Nov 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What is the Scrapling MCP server?
- Is Scrapling safe to connect to an agent?
- What credentials does Scrapling need?