Browser Bridge (mukeshblackhat) MCP Server
browser-bridge-mcp
npm
v0.2.0
Published by mukeshblackhat — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
Give Claude Code direct access to your browser - console, network, errors, storage, DOM and more
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 22.9 = 77. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −15.4 | Assembled command execution and dynamic evaluation in the same server MTC-SRC-011 | injection |
| −6.3 | Untrusted input concatenated into a command sink MTC-SRC-009 | injection |
| −1.2 | Package runs install-time scripts MTC-SUP-010 | supply-chain |
2. Client adoption risk — 77 − 11 = 66. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −10 | capability blast radius (critical) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 6
high Dynamic evaluation of a non-literal value (src/client.js)MTC-SRC-010
In the server's implementation (`src/client.js:532`): Evaluating a runtime value as code (rather than a fixed literal) executes whatever reaches it — a direct RCE primitive, and almost never necessary in legitimate code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const result = eval(params.code); return { success: true, result: serializeArg(result) }; } c
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/client.js
high Assembled command execution and dynamic evaluation in the same serverMTC-SRC-011
The implementation both builds shell commands out of runtime values (`bin/cli.mjs`) and evaluates runtime values as code (`src/client.js`). Each is a separate arbitrary-execution primitive; a server exposing both gives anything that reaches either one a direct path to running attacker-chosen code. These two sinks are in different files — confirm whether they are actually connected, or are unrelated code paths (e.g. a vendored bundle plus a CLI wrapper).
Fix: Remove the dynamic eval, and pass command arguments as an argv array instead of building a shell string. If both are genuinely required, constrain and validate every value that can reach them.
Location: server implementation
high Dynamic code execution in server code (src/client.js)MTC-SRC-001
In the server's implementation (`src/client.js:532`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const result = eval(params.code); return { success: true, result: serializeArg(result) }; } c
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/client.js
high Shell/command execution in server code (bin/cli.mjs)MTC-SRC-002
In the server's implementation (`bin/cli.mjs:15`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: port { execSync } from "child_process"; import { readFileSync, writeFileSync } from "fs"; import { fileURLToPath } from
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server bin/cli.mjs
medium Untrusted input concatenated into a command sink (bin/cli.mjs)MTC-SRC-009
In the server's implementation (`bin/cli.mjs:131`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: m === "darwin") { execSync(`open "${outPath}"`); } else if (platform === "linux") { execSync(`xdg-open "
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server bin/cli.mjs
low Package runs install-time scripts (postinstall)MTC-SUP-010
"browser-bridge-mcp" executes postinstall script(s) at install time. An install hook runs at install time; most are routine build/setup, but review what it does before trusting it.
Evidence: node bin/postinstall.mjs
Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.
Location: package browser-bridge-mcp
Tools 15
Each tool and what it can reach — statically extracted from the published source.
browser_get_page_infoingests untrusted inputbrowser_clear_allno sensitive capabilitybrowser_execute_jsno sensitive capabilitybrowser_focus_tabno sensitive capabilitybrowser_get_console_logsno sensitive capabilitybrowser_get_cookiesno sensitive capabilitybrowser_get_dom_snapshotno sensitive capabilitybrowser_get_errorsno sensitive capabilitybrowser_get_local_storageno sensitive capabilitybrowser_get_network_requestsno sensitive capability
Show 5 more tools ↓
browser_get_performanceno sensitive capabilitybrowser_get_react_query_cacheno sensitive capabilitybrowser_get_redux_stateno sensitive capabilitybrowser_get_session_storageno sensitive capabilitybrowser_list_connectionsno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (15 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.2.0 latest |
D 66/100 | 6 | 1.13.0 | 2026-09-07 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan browser-bridge-mcp --onlineOther implementations of Browser Bridge 2
Independent packages implementing the same tool, scanned with the same engine. Compare all 3 side by side →
Connects AI assistants to the browser through a WebSocket-connected browser extension.
Chrome MCP Server — AI controls your real browser with full HTML/CSS/JS access
More in Developer Tools
Hotel booking MCP server — 300K+ properties, real confirmation numbers, loyalty programs. Builders monetize every booking via Stripe Connect. The first MCP server that completes real hotel reservations inside AI conversations.
Manage AdGuard Home through AI assistants
Read-only Azure DevOps for MCP clients using only your existing browser session — no PAT, no Azure CLI. Browse work items, pull requests, comments, attachments and Artifacts feeds across every project, repo and feed you can access.
MCP server for Adobe Experience Manager Assets integration development
Servidor MCP para el tiempo oficial de España (API pública OpenData de AEMET). Predicción, observación y avisos como herramientas MCP tipadas.
A standalone MCP stdio bridge for Affinity by Canva's local MCP SSE server.