Atlas / MCP servers / kunchenguid / chrome-devtools-axi

chrome-devtools-axiBLOCK

mcp/kunchenguid/chrome-devtools-axi

The most agent-ergonomic browser automation

Verdict
BLOCK
Grade
D
Trust score
69 /100
Exposed tools
1 1r · 0w · 0d
Transport
stdio · streamable-http
License
MIT
Stars
415
01

Overview

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

chrome-devtools-axi

The most agent-ergonomic browser automation

chrome-devtools-axi wraps chrome-devtools-mcp with an AXI-compliant CLI.

  • Token-efficient — TOON-encoded output cuts token usage ~40% vs raw JSON
  • Combined operations — one command navigates, captures, and suggests next steps
  • Contextual suggestions — every response includes actionable next-step hints

Benchmarks

Agent ergonomics is measurable. The axi benchmark runs the same 14 real-world browsing tasks (Wikipedia research, GitHub navigation, multi-site comparison, and more) through 7 browser automation setups - 5 repeats each, with claude-sonnet-4-6 as the agent and an LLM judge scoring task success.

chrome-devtools-axi posts the lowest input

Read from source at commit 349d3541b7a7OBSERVED · 2026-10-12
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 chrome-devtools-axi -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "chrome-devtools-axi": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  }
}
03

Exposed tools (1)

1 read · 0 write · 0 destructive.

ToolRiskDescription
list_pagesread
04

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.

LayerWhat it checksResult
L0Provenance & inventoryWARN
L1Static analysis of the codeFAIL
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
declared (4 observation(s))
Shell
declared (2 observation(s))
Dependencies
not all pinned
Secrets in source
none-found

Findings (17)

HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
src/run.ts:157
eval(jsOrFn: string | ((...args: unknown[]) => unknown)): Promise<unknown>;
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
MEDIUMInventory / provenance · inv.symlink · CWE-1104
.claude/skills
.claude/skills
Why it matters. link not followed
MEDIUMNetwork egress · net.raw_ip · CWE-200, CWE-319
src/bridge.ts:1208
logBridgeMessage(`Listening on http://127.0.0.1:${port}`);
MEDIUMNetwork egress · net.raw_ip · CWE-200, CWE-319
src/cli.ts:92
e.g. "http://127.0.0.1:9222" or "wss://cluster.example/launch"
LOWInventory / provenance · inv.hidden_file · CWE-1104
.prettierignore
.prettierignore
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.hidden_file · CWE-1104
.release-please-manifest.json
.release-please-manifest.json
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
test/main.test.ts:307
const compiled = new Function(
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
test/main.test.ts:332
const compiled = new Function(
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
test/run.test.ts:312
const pending = new Function(`return (${args.function})`)()();
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
test/run.test.ts:354
new Function(`return (${args.function})`)()(),
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
LOWFilesystem / path · fs.credential_store · CWE-22, CWE-59
test/client.test.ts:1501
filePaths: ["/home/user/.ssh/id_rsa"],
Why it matters. touches a credential store
LOWFilesystem / path · fs.system_paths · CWE-22, CWE-59
test/hooks.test.ts:165
command: "/usr/local/bin/chrome-devtools-axi",
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
README.md:327
export CHROME_DEVTOOLS_AXI_MCP_SERVER_URL=http://127.0.0.1:9333/mcp
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
README.md:344
export CHROME_DEVTOOLS_AXI_MCP_SERVER_URL=http://127.0.0.1:9333/mcp
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
README.md:372
export CHROME_DEVTOOLS_AXI_BROWSER_URL=http://127.0.0.1:9222
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@modelcontextprotocol/sdk, @toon-format/toon, axi-sdk-js, @types/node, prettier, tsx, typescript, vitest
Why it matters. 9 dependency range(s) float
Fix. pin exact versions or ship a lockfile
INFOPrompt injection · prompt.credential_read · CWE-94, CWE-1427
README.md:417
Your own externally launched Chrome is unaffected: its saved passwords remain available and untouched because this tool does not read, write, move, or reset the login keychain or its `Chrome Safe Stor
Why it matters. asks the agent to read credentials

Gates applied: no_behavioural_pass.

Audited 2026-10-12 · audit v0.4.1 · source sha 349d3541b7a7full audit observations/trust-audit/mcp-server/kunchenguid__chrome-devtools-axi.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
2026-10-12349d3541b7a7BLOCKD69first audit
06

Questions

What is the chrome-devtools-axi MCP server?

The most agent-ergonomic browser automation

What tools does chrome-devtools-axi expose?

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

Is chrome-devtools-axi 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.

What credentials does chrome-devtools-axi need?

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

How does chrome-devtools-axi run?

It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as chrome-devtools-axi at 0.1.40.

How current is this page?

The grade is for one exact copy of the source (349d3541b7a7), read on 2026-10-12. The repository is watched and re-audited when it changes.

Advertisement