Field-by-field comparison

Compare the evidence before choosing an MCP.

Each signal stays separate, missing facts remain visible, and the column order follows your selection.

MCPs in this comparison

JADX-AI-MCP (Part of Zin MCP Suite)Chrome DevTools MCP

Uncheck an MCP to remove it. Comparing two or three keeps each signal in its own row.

Comparable alternatives

Azure MCP ServerMCP100 SelectedContext7 MCPMCP100 SelectedFirecrawl MCPMCP100 SelectedGrafana Cloud MCPMCP100 SelectedMCP Server for WinDbg Crash AnalysisMCP100 SelectedGoogle MCP Toolbox for DatabasesMCP100 Selected

Shown only when capability or industry context overlaps.

Side-by-side MCP evidence comparison
Evidence field	JADX-AI-MCP (Part of Zin MCP Suite)MCP100 Selected	Chrome DevTools MCPMCP100 Selected
Task fit
Best for	Navigating JADX decompilation, searching APK code, and accelerating reverse-engineering or security-analysis hypotheses	Inspecting pages, console and network activity, automating browser actions, and collecting performance evidence in Chrome
Not ideal for	Definitive vulnerability certification, dynamic analysis, or reviewing applications without authorization	API-only testing or browsers outside the project's documented Chrome support
Avoid when	APK contents, decompiled code, or findings cannot be shared with the connected AI client	The controlled browser contains personal accounts, secrets, or sessions that the MCP client must not inspect or modify
Provenance
Provenance details	Community implementation github:zinja-coder · Publisher source ↗	Community implementation io.github.ChromeDevTools · Publisher source ↗
Maintenance
Maintenance details	Repo: Aug 6, 2026 Package: Not documented	Repo: Aug 14, 2026 Package: Aug 10, 2026
Popularity evidence
GitHub stars	2,664 GitHub stars · checked 2026-08-14T18:46:26.000Z	49,168 GitHub stars · checked 2026-08-14T18:46:26.000Z
30-day package downloads	No reliable download data	7,541,930 30-day package downloads · checked 2026-08-14T18:46:26.000Z
External adoption evidence	github: repository stars: 2,664Exact attributable signal.github: repository stars · Admission snapshot · checked 2026-08-14T18:46:26.000ZEvidence source ↗	github: repository stars: 49,168Exact attributable signal.github: repository stars · Admission snapshot · checked 2026-08-14T18:46:26.000ZEvidence source ↗
Client coverage
Client coverage details	Claude Code✓ Local stdio Claude Desktop✓ Local stdio Codex✓ Local stdio VS Code✓ Local stdio Cursor✓ Local stdio OpenCode✓ Local stdio	Claude Code✓ Local stdio Claude Desktop✓ Local stdio Codex✓ Local stdio VS Code✓ Local stdio Cursor✓ Local stdio OpenCode✓ Local stdio
Client coverage note	Local stdio runs on your computer. Streamable HTTP connects to a remotely hosted MCP server.
Access and data
Authentication	The documented default is stdio with the HTTP endpoints on 127.0.0.1. The publisher explicitly warns that binding the MCP server to 0.0.0.0 or another non-localhost address exposes plain HTTP with no authentication or TLS, allowing anyone on that network to invoke all tools.	No server authentication is documented for local stdio. Running-browser connections support optional WebSocket headers; an open remote-debugging port lets local applications control Chrome.
Cost	The publisher distributes the project under the Apache License 2.0 and lists no MCP server usage fee. JADX, local compute, the selected MCP client, and model-provider costs can still apply.	The open-source npm package lists no MCP fee. Chrome, Node.js, client, model, and external-service costs are separate.
Permissions	The published tools can read decompiled code for classes and methods, smali, AndroidManifest.xml, string and resource files, cross-references, and debugger frames, threads, and variables from the project open in JADX. They can also rename classes, methods, fields, packages, and variables within the JADX analysis workspace.	Inspects, debugs, automates, and modifies browser state through navigation, input, script evaluation, screenshots, uploads, extensions, memory, performance, and PWA tools.
Data handling	The publisher's architecture sends tool requests from the LLM client through the Python MCP server over HTTP to the JADX-GUI plugin, then returns source, resource, manifest, and debugger data to the connected client. The reviewed README does not document telemetry, retention, or model-training use, so those behaviors remain unknown.	Browser content is exposed to the connected client. Performance tools send trace URLs to Google CrUX by default, and usage statistics with invocation success, latency, and environment data are enabled by default; broader retention is not documented.
Limitations
Tradeoffs	JADX integration speeds static exploration, but decompilation is imperfect and AI-generated security conclusions can contain false positives or miss runtime behavior.	Deep DevTools access improves debugging, but exposes browser content and state; usage statistics and CrUX URL lookups are enabled by default unless disabled.
Risk context	This server exposes sensitive reverse-engineering material and mutation tools for the APK project open in JADX. Keep both connections on 127.0.0.1 and prefer stdio; if remote access is unavoidable, use a trusted isolated network plus firewall or SSH tunnel. Treat decompiled source, resources, manifests, and debugger values as potentially confidential, and review rename operations before saving or exporting analysis artifacts.	Can expose sensitive browser sessions and execute arbitrary browser actions or scripts. Use isolated profiles, URL allow/block patterns, restricted file paths, and do not expose remote-debugging ports.
Evidence date
Editorial review	2026-08-11	2026-08-11
Candidate evidence	2026-08-14T18:46:26.000Z	2026-08-14T18:46:26.000Z

Popularity, maintenance, fit, permissions, and client support are independent evidence fields.

Read the evidence method →