hanzi-browse (hanzili/hanzi-browse) is an MCP server listed on the M8ven Trust Index. It scores 89 out of 100, grade B. It declares 10 tools. No publisher has claimed this listing.

Caution

89/100

1 month ago

hanzi-browse

Item: hanzi-browse
Rating: 89
Author: M8ven

let any ai agent use the local browser

→ hanzili/hanzi-browse · listed on glama

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every push why connect →

Who stands behind it

hanzili

Source: Glama · also listed on github_topic

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

Glama GitHub

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings

🚨

Secret credentials may flow to a network call

9 flows detected: HANZI_API_URL, TEST_API_URL. We can’t prove the destination matches the brand the credential belongs to.

⚠️

Known vulnerabilities in dependencies: 1 high

Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.

🔐

You'll be asked for 9 credentials: ANTHROPIC_API_KEY, BETTER_AUTH_SECRET, GOOGLE_CLIENT_SECRET, HANZI_API_KEY, POSTHOG_API_KEY, RELAY_SECRET, STRIPE_SECRET_KEY, STRIPE_WEBHOOK_SECRET, TEST_API_KEY

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// known CVEs in dependencies1 high1 medium1 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

highvite@8.0.10GHSA-fx2h-pf6j-xcff

vite: `server.fs.deny` bypass on Windows alternate paths

mediumvite@8.0.10GHSA-v6wh-96g9-6wx3

launch-editor: NTLMv2 hash disclosure via UNC path handling on Windows

low@babel/core@7.28.6GHSA-4x5r-pxfx-6jf8

@babel/core: Arbitrary File Read via sourceMappingURL Comment

Depend on this server? Get alerted when its CVEs change.Watch this server free →

// environment variables

To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.

🔐 secretANTHROPIC_API_KEY

configAPI_PORT

🔐 secretBETTER_AUTH_SECRET

configBETTER_AUTH_URL

configDO_NOT_TRACK

configGOOGLE_CLIENT_IDGoogle OAuth (dashboard sign-in) -- add / GOOGLE_CLIENT_SECRET to .env

🔐 secretGOOGLE_CLIENT_SECRETGoogle OAuth (dashboard sign-in) -- add GOOGLE_CLIENT_ID / to .env

🔐 secretHANZI_API_KEYconst client = new HanziClient({ apiKey: process.env. });

configHANZI_API_URL

configHANZI_BROWSE_MAX_SESSIONS

configHANZI_BROWSE_SESSION_TTL_MS

configHANZI_BROWSE_TIMEOUT_MS

configHANZI_DASHBOARD_URL

configHANZI_EVAL_SESSION_ID

configHANZI_RELAY_URL

configHANZI_SESSION_TTL_MS

configHANZI_TELEMETRY

configHTTPS_PROXY

configHTTP_PROXY

🔐 secretPOSTHOG_API_KEYPostHog (analytics) -- add to enable local CLI telemetry, dashboard analytics, managed backend analytics, and the example apps; optionally set POSTHOG_HOST

configPOSTHOG_HOSTPostHog (analytics) -- add POSTHOG_API_KEY to enable local CLI telemetry, dashboard analytics, managed backend analytics, and the example apps; optionally set

configPROXY_URL

configRELAY_HOST

configRELAY_PORT

🔐 secretRELAY_SECRET

configRELAY_URL

configSTRIPE_API_METER_ID

configSTRIPE_CREDIT_PRICE_ID

🔐 secretSTRIPE_SECRET_KEY

🔐 secretSTRIPE_WEBHOOK_SECRET

🔐 secretTEST_API_KEY

configTEST_API_URL

configVERTEX_SA_JSON

configVERTEX_SA_PATH

configVITEST

configWS_RELAY_PORT

configXDG_CONFIG_HOME

confighttp_proxy

confighttps_proxy

Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.

deployDATABASE_URL

deployPORT

deploySENTRY_DSN

// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

10/10 tools missing one or more hints — browser_start (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); browser_message (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); browser_status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +7 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool test coverage

Only 0/10 tools referenced in tests (0%)

Write tests that reference each tool by name so every tool has at least one test.

Shell command execution

1 child_process call — runs shell commands

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

Secrets stay with their owner

5 secret/sensitive values flow into network calls (TEST_API_URL → dynamic, TEST_API_URL → dynamic) (4 other flows matched canonical API hosts)

Audit where credentials are sent. A NOTION_TOKEN should only reach api.notion.com — never a third-party host.

Secrets not logged

5 secret values sent to console.log

Redact or omit secret values from log output.

Dev dependencies

1 critical/high in dev-only deps (does not ship to users)

Upgrade dev dependencies when convenient.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail

The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.

// improvement guidance — verified publishers only

We have 7 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Verified](https://m8ven.ai/badge/mcp/hanzili/hanzi-browse?variant=verified)](https://m8ven.ai/mcp/hanzili/hanzi-browse)

Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.

commit: ce6e10dc0e09afdf88b481afc5e8339bee745918

code hash: 907290862cd4846463c7768b9ab8df476b809dec163927b933b955b89144e3d7

verified: 8/6/2026, 3:03:20 PM

view raw JSON →

Check MCPs from inside your assistant

Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check

check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern

How to add it →Free · no account needed · works in any MCP client