scrapewise-mcpSAFE
ScrapeWise MCP server - hosted remote MCP for scraping product and price data from any website
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Scrape, clean and match product and price data from any website — from inside your AI agent.
ScrapeWise runs a hosted Model Context Protocol server. You point your MCP client at one URL and add your API key. Your agent can then find local businesses, search Google and Amazon, fetch web pages and read the rows saved in your account. Add ?toolsets=outcome,admin to the URL and it also builds and runs scrapers.
- Endpoint:
https://mcp.scrapewise.ai/mcp - Endpoint with the setup tools (to build scrapers):
https://mcp.scrapewise.ai/mcp?toolsets=outcome,admin - Transport: Streamable HTTP
- Registry name:
ai.scrapewise/scrapewise(official MCP registry) - Auth:
Authorization: Bearer - Docs: scrapewise.ai/mcp
This repository holds the connection manifest and the per-client config for that server. The server itself is hosted — there is nothing here to install or run.
Get an API key
Sign up at scrapewise.ai, then go to Settings → API Keys and create one. Pricing is pay-as-you-go.
Connect
Replace YOUR_SCRAPEWISE_API_KEY in every snippet below.
These snippets connect to the short list of data tools. To build scrapers as well, use this address in the same place:
https://mcp.scrapewise.ai/mcp?toolsets=outcome,admin
An account that gets its first MCP key now sees only the short list at the bare address. Accounts that still hold an older MCP key keep every tool. The choice is read when the session starts, so reconnect after changing it. Spell it toolsets: a misspelt switch is ignored without an error.
Claude Code
claude mcp add scrapewise --transport http https://mcp.scrapewise.ai/mcp \ --header 'Authorization: Bearer YOUR_SCRAPEWISE_API_KEY'
With the setup tools. The single quotes are needed: in zsh an unquoted ? breaks the
f3fc4adc4645OBSERVED · 2026-10-11Trust 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.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (2)
streamable-http
Gates applied: no_behavioural_pass.
f3fc4adc4645full audit observations/trust-audit/mcp-server/bebotech-ou__scrapewise-mcp.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 | f3fc4adc4645 | SAFE | B | 89 | first audit |
Questions
What is the scrapewise-mcp MCP server?
ScrapeWise MCP server - hosted remote MCP for scraping product and price data from any website
Is scrapewise-mcp 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.
What credentials does scrapewise-mcp need?
No credential environment variables were found in its source, so it appears to need none.
How does scrapewise-mcp run?
It speaks streamable-http, so it runs as a service you connect to over the network.
How current is this page?
The grade is for one exact copy of the source (f3fc4adc4645), read on 2026-10-11. The repository is watched and re-audited when it changes.