Atlas / MCP servers / pipeworx-io / mcp-zyte

mcp-zyteSAFE

mcp/pipeworx-io/mcp-zyte

Zyte API MCP — unified web fetch + AI extraction (zyte.com)

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
3 2r · 1w · 0d
Transport
stdio · streamable-http
License
MIT
Stars
0
01

Overview

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

Zyte API MCP — unified web fetch + AI extraction (zyte.com)

Part of Pipeworx — an MCP gateway connecting AI agents to 1684+ live data sources.

Tools

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
"mcpServers": {
"zyte": {
"url": "https://gateway.pipeworx.io/zyte/mcp"
}
}
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/zyte/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools

Read from source at commit 28f494a16cc5OBSERVED · 2026-10-11
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.

claude-code
claude mcp add mcp-zyte -- npx -y @pipeworx/[email protected]
claude-desktop
{
  "mcpServers": {
    "mcp-zyte": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/[email protected]"
      ]
    }
  }
}
03

Exposed tools (3)

2 read · 1 write · 0 destructive.

ToolRiskDescription
zyte_extractwriteAI-powered automatic extraction of structured data from a web page. Set type to
zyte_fetchreadFetch a web page through Zyte API and return its content. By default returns the raw HTTP response body (decoded to text). For JS-heavy sites that need a real browser, pass render:true to get browser-rendered HTML instead. Example: zyte_fetch({ url:
zyte_screenshotreadCapture a screenshot of a web page via Zyte API (rendered in a headless browser). Returns metadata about the base64-encoded PNG (its length) rather than inlining the full blob. Example: zyte_screenshot({ url:
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 surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
declared (1 observation(s))
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (3)

LOWObfuscation / stealth · obf.decode_call · CWE-506, CWE-94
src/index.ts:825
const bin = atob(b64);
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@modelcontextprotocol/sdk, tsx, typescript, @cloudflare/workers-types
Why it matters. 4 dependency range(s) float
Fix. pin exact versions or ship a lockfile
LOWPrompt injection · prompt.transfer_instruction · CWE-94, CWE-1427
README.md:65
This pack takes your own API key (`_apiKey`) — we don't front one for it, so there's no curl here that would run without it. Inspect any tool: `GET https://gateway.pipeworx.io/v1/tools/zyte_fetch`. Fi
Why it matters. an instruction to move sensitive data to an outside destination
Fix. remove; a skill never needs the user's secrets off the machine

Gates applied: no_behavioural_pass.

Audited 2026-10-11 · audit v0.4.1 · source sha 28f494a16cc5full audit observations/trust-audit/mcp-server/pipeworx-io__mcp-zyte.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
2026-10-1128f494a16cc5SAFEB89first audit
06

Questions

What is the mcp-zyte MCP server?

Zyte API MCP — unified web fetch + AI extraction (zyte.com)

What tools does mcp-zyte expose?

3 in total: 2 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is mcp-zyte 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 mcp-zyte need?

No credential environment variables were found in its source, so it appears to need none.

How does mcp-zyte run?

It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as @pipeworx/mcp-zyte at 0.1.2.

How current is this page?

The grade is for one exact copy of the source (28f494a16cc5), read on 2026-10-11. The repository is watched and re-audited when it changes.

Advertisement