Skills/PyPI/mcp-server-browser-use

mcp-server-browser-use@0.1.9

VERIFIED· not started

Publisher claims: "MCP server for browser-use" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher igor-tarasenko · publishing for 663 daysInstalls 300Last detonated 4d ago
$claude mcp add mcp-server-browser-use -- uvx mcp_server_browser_use
WatchReport an issue

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
IBM_API_KEYMISTRAL_API_KEYMOONSHOT_API_KEYSiliconFLOW_API_KEYSKIP_LLM_API_KEY_VERIFICATIONConfiguration, not credentials: ALIBABA_ENDPOINT, AZURE_OPENAI_API_VERSION, AZURE_OPENAI_ENDPOINT, CHROME_PATH, CHROME_USER_DATA, DEEPSEEK_ENDPOINT, IBM_ENDPOINT, IBM_PROJECT_ID, MCP_RESEARCH_TOOL_SAVE_DIR, MCP_SERVER_LOGGING_LEVEL, MISTRAL_ENDPOINT, MOONSHOT_ENDPOINT, OLLAMA_ENDPOINT, OPENAI_ENDPOINT, SiliconFLOW_ENDPOINT, UNBOUND_ENDPOINT
Where it talks to
no vendor host named in the codeAlso mistral.ai, aliyuncs.com, ibm.com, getunbound.ai, openrouter.ai — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names mistral.ai, aliyuncs.com, ibm.com, getunbound.ai, openrouter.ai as well as its own vendor. The guard injects IBM_API_KEY, MISTRAL_API_KEY, MOONSHOT_API_KEY, SiliconFLOW_API_KEY, SKIP_LLM_API_KEY_VERIFICATION only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx mcp_server_browser_use

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-10 and scored it 84/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
URL with suspicious TLDsrc/mcp_server_browser_use/_internal/utils/llm_provider.py:286 · URL with suspicious TLD — commonly used for phishing/malwarebase_url = os.getenv("IBM_ENDPOINT", "https://us-south.ml.cloud.ibm.com")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Process kill commandsrc/mcp_server_browser_use/_internal/browser/custom_browser.py:116 · Process kill command — agent can terminate processes# always kill all children processes, otherwise chrome leaves a bunch of zombie processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/mcp_server_browser_use/cli.py:67 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Reload settings after .env might have been loaded and to apply overridesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mcp_server_browser_use/cli.py:53 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesNone, "--env-file", "-e", help="Path to .env file to load.", exists=True, dir_okay=False, resolve_path=TrueFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mcp_server_browser_use/cli.py:61 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesYou can use an .env file for convenience.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈626 tok
2 files · 27 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for mcp_server_browser_use@0.1.9 as of 4d ago. This is the package itself, not its dependencies.