Crawlio Browser — Watchlist

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Follow-up value is specific to Crawlio live Chrome automation and evidence collection: Do extension permissions make access to logged-in sessions explicit as storage and network-capture tools change?

Reviewed Oct 5, 2026 · Documentation review; complete setup workflow not independently tested

Best fit

Full-control automation of a live Chrome session through CDP for capture, extraction, network and workflow automation.

What we know

Chrome-extension + MCP bridge giving an agent control over connected tabs, with code/full modes, stdio or persistent local HTTP portal, and strong session observability.

Maintenance / activity evidence

crawlio-browser 1.11.0 published 2026-08-10T05:29:47.321Z

Tracking evidence observed Oct 5, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: high.

Verification gaps / watch-outs

Installation and comprehensive security have not been independently audited.
Very broad browser/session authority over connected tabs. Writes: Click/type/submit forms; Navigate authenticated sites; Mutate web-app state; Potentially trigger purchases/admin actions depending on site.
Uses the browser's existing authenticated sessions.
Sensitive access: Cookies, Local/session storage, Authenticated web data, Credentials entered in browser

High blast radius because agent can act as logged-in user; use dedicated Chrome profile and explicit target review.

Full authority, access and evidence limits are available in Review context and Access & risk.

All limitations / Review context

Do extension permissions make access to logged-in sessions explicit as storage and network-capture tools change?

The bounded review of the publisher's documented Crawlio live Chrome automation and evidence collection and release notices identified no disclosed material condition preventing an accurately scoped public tracking entry. The resource's operational permissions remain uncertainty; this assessment does not certify installation safety.

High blast radius because agent can act as logged-in user; use dedicated Chrome profile and explicit target review.
Very broad browser/session authority over connected tabs.
Uses the browser's existing authenticated sessions.
Connected page content, cookies/storage and browser state become available to the agent for that tab/session.
Reviewed write actions: Click/type/submit forms; Navigate authenticated sites; Mutate web-app state; Potentially trigger purchases/admin actions depending on site
Sensitive access: Cookies, Local/session storage, Authenticated web data, Credentials entered in browser
Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited.
Documented tool authority and any remote data handling must be checked before installation or use.
Tool inventory, client matrix and permissions completeness were not requirements for this Radar tracking review.
Connecting an authenticated tab lets the agent act as the user on that site.
The tool surface is large/dynamic and mode-dependent.
Requires extension/bridge setup; dedicated browser profile is strongly recommended.

Original activity observations

crawlio-browser 1.11.0 published 2026-08-10T05:29:47.321Z

Technical identity

npm/crawlio-browser

Exact implementation source: https://www.npmjs.com/package/crawlio-browser ↗
Reviewed resource type: MCP Server
Repository identity: Crawlio-app/crawlio-browser
Package identity: npm:crawlio-browser
Service endpoint: http://127.0.0.1:3001/mcp (portal mode)

Evidence & Sources

Evidence basis: Recorded source evidence
Setup runtime verification: Not independently runtime-tested by MCP100 for this setup workflow.

Reviewed Oct 5, 2026 · Latest source observation Oct 8, 2026

Package registry metadata ↗
crawlio-browser
Recorded package identity, distribution or download evidence.
GitHub repository ↗
crawlio-app/crawlio-browser
Repository reference; implementation attribution is not established for every document.
Includes references whose attribution is not established.

Setup · Watchlist

Install & Agents

Publisher instructions.

Source evidence observed Oct 14, 2026.

Additional setup details required — see the specific gaps below.

Warning

Not runtime tested, no third-party installation, network authorization, paid calls, or mutation executed.
Do not claim production service is available based on README alone.
Browser automation; init modifies client configuration, may use native host/extension; browser automation not innocuous
Init changes MCP client config and may install browser native host; show dry-run before actual change.
Official npm publisher package page README inspected for this exact npm identity; static research only. Some setup statements are conservatively summarized; no source code or live client execution checked. V2 review did not run any live client.
Check actual host syntax and supply credentials in secure client environment; do not paste placeholders verbatim.
Avoid write, payment, token transfer, publishing, sending, booking and remote account changes as tests.
Replace credential, action and registration placeholders; follow the matching publisher/client prerequisites. No execution performed.
Use the matching host, actual registration name and original installation environment; this does not revoke credentials.

Install / connect
Publisher instructions
Browser automation; init modifies client configuration, may use native host/extension; browser automation not innocuous | Publisher npm README revisited on 2026-10-14; exact identity retained.
Reviewed setup example · Publisher instructions
npx crawlio-browser init --dry-run
Reviewed setup example · Publisher instructions
npx crawlio-browser init
Reviewed setup example · Publisher instructions
npx crawlio-browser doctor
Configure / authenticate
MCP100 setup guide
Install publisher Chrome extension, then run `npx crawlio-browser init` for selected host; `--dry-run` previews changes.
Check connection
Suggested check
`npx crawlio-browser doctor` checks bridge and client configs, then inspect browser connection separately.
Remove / uninstall / revoke
MCP100 setup guide
If your Claude Code MCP registration is named `crawlio-browser`, run the client removal command. For Claude Desktop/Cursor/Codex or another registered name, remove the matching entry in that host’s MCP settings. Hosted OAuth disconnect and stopping a self-hosted process are separate; npx has no permanent global package install.
Remove named client registration · Claude Code only · MCP100 composed guide
claude mcp remove crawlio-browser

Official Documentation & Sources

What it does

Chrome-extension + MCP bridge giving an agent control over connected tabs, with code/full modes, stdio or persistent local HTTP portal, and strong session observability.

Capability: Browser Automation
Resource type: MCP Server
Best fit: Full-control automation of a live Chrome session through CDP for capture, extraction, network and workflow automation.

Representative uses

Navigate/click/type in live Chrome
Read DOM/page/network/cookies/storage
Capture/extract structured data
Record sessions and run browser automation

Limitations

Connecting an authenticated tab lets the agent act as the user on that site.
The tool surface is large/dynamic and mode-dependent.
Requires extension/bridge setup; dedicated browser profile is strongly recommended.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: Uses the browser's existing authenticated sessions.
Permissions: Very broad browser/session authority over connected tabs.
Data handling: Connected page content, cookies/storage and browser state become available to the agent for that tab/session.
Cost: free_open_source
Risk and cautions: High blast radius because agent can act as logged-in user; use dedicated Chrome profile and explicit target review.

Access scope and cautions

Write actions: Click/type/submit forms Navigate authenticated sites Mutate web-app state Potentially trigger purchases/admin actions depending on site
Sensitive access: Cookies Local/session storage Authenticated web data Credentials entered in browser
Risk level: high

FAQ

Based on reviewed evidence as of 2026-10-08. Watchlist tracking is not a recommendation or a security certification.

Which tasks are documented for this implementation?

The reviewed tasks include: Navigate/click/type in live Chrome; Read DOM/page/network/cookies/storage; Capture/extract structured data; Record sessions and run browser automation.

What setup and authentication are documented?

Recorded installation/entrypoint step: npx crawlio-browser init. Recorded transport: stdio, streamable_http, sse. Prerequisites: Chrome extension; Node/npm; MCP client. These are the documented setup details, not a claim that installation or client compatibility was independently tested. Authentication: Local bridge/extension; target websites may have their own login sessions.

Can it modify data or perform write operations?

Documented write actions include: Click/type/submit forms; Navigate authenticated sites; Mutate web-app state; Potentially trigger purchases/admin actions depending on site. Recorded permission boundary: Very broad browser/session authority over connected tabs.

What data-handling boundary should I consider?

Connected page content, cookies/storage and browser state become available to the agent for that tab/session. Recorded sensitive-access context: Cookies; Local/session storage; Authenticated web data; Credentials entered in browser.

What limitations and risks should I check before use?

High blast radius because agent can act as logged-in user; use dedicated Chrome profile and explicit target review. Connecting an authenticated tab lets the agent act as the user on that site. The tool surface is large/dynamic and mode-dependent. Requires extension/bridge setup; dedicated browser profile is strongly recommended. Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited. Documented tool authority and any remote data handling must be checked before installation or use.