Google Surf MCP Server
google-surf-mcp
npm
v1.0.9
Published by harimxchoi — 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.
MCP server for Google search via warm Chrome profile. No API key.
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 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 7 = 93. 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 |
|---|---|
| −6 | capability blast radius (high) — 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 12
high Reads a sensitive credential path or dumps the environment (build/research/inventory.js)MTC-SRC-006
In the server's implementation (`build/research/inventory.js:22`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: E_NAMES = new Set([ '.netrc', '.npmrc', '.pypirc', 'auth.json', 'credentials.json', 'token.json', ]); const SECRET_P
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 build/research/inventory.js
high Shell/command execution in server code (build/browser.js)MTC-SRC-002
In the server's implementation (`build/browser.js:1`): 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: ecFileSync } from 'node:child_process'; import { existsSync } from 'node:fs'; import { rm, cp, readdir } from 'node:fs/p
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 build/browser.js
high Shell/command execution in server code (build/collect.js)MTC-SRC-002
In the server's implementation (`build/collect.js:3`): 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: ecFileSync } from 'node:child_process'; import { createHash } from 'node:crypto'; import { dirname, resolve } from 'node
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 build/collect.js
high Shell/command execution in server code (build/nativeBrowser.js)MTC-SRC-002
In the server's implementation (`build/nativeBrowser.js:1`): 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: rt { spawn } from 'node:child_process'; import { mkdir } from 'node:fs/promises'; import { createServer } from 'node:net
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 build/nativeBrowser.js
high Shell/command execution in server code (build/nativeBrowserBroker.js)MTC-SRC-002
In the server's implementation (`build/nativeBrowserBroker.js:1`): 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: rt { spawn } from 'node:child_process'; import { randomBytes, randomUUID } from 'node:crypto'; import { existsSync } fro
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 build/nativeBrowserBroker.js
high Shell/command execution in server code (build/notify.js)MTC-SRC-002
In the server's implementation (`build/notify.js:1`): 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: rt { spawn } from 'node:child_process'; import { platform } from 'node:os'; function spawnDetached(cmd, args) { retu
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 build/notify.js
high Shell/command execution in server code (build/research/broker.js)MTC-SRC-002
In the server's implementation (`build/research/broker.js:1`): 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: rt { spawn } from 'node:child_process'; import { createHash, randomBytes, randomUUID } from 'node:crypto'; import { exis
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 build/research/broker.js
high Shell/command execution in server code (build/research/github.js)MTC-SRC-002
In the server's implementation (`build/research/github.js:1`): 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: rt { spawn } from 'node:child_process'; import { mkdir, stat } from 'node:fs/promises'; import { join, resolve } from 'n
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 build/research/github.js
high Shell/command execution in server code (build/research/projectInventory.js)MTC-SRC-002
In the server's implementation (`build/research/projectInventory.js:1`): 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: ecFileSync } from 'node:child_process'; import { createHash } from 'node:crypto'; import { lstat, readFile, readdir } fr
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 build/research/projectInventory.js
medium Hardcoded egress to an external endpoint (build/heal/llm.js)MTC-SRC-003
In the server's implementation (`build/heal/llm.js:101`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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 response = await fetch('https://api.orcarouter.ai/v1/chat/completions', { method: 'POST', headers
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 build/heal/llm.js
medium Dynamic module load from a non-literal (build/heal/llm.js)MTC-SRC-005
In the server's implementation (`build/heal/llm.js:73`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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 mod = await import(sdkName); Anthropic = mod.default; } catch { throw new Error('ANT
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 build/heal/llm.js
medium Dynamic module load from a non-literal (build/research/dense.js)MTC-SRC-005
In the server's implementation (`build/research/dense.js:60`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: extractorFactory?.() ?? import(runtimeUrl.href) .then(async ({ pipeline }) => await pipeline('feature-extrac
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 build/research/dense.js
Tools 7
Each tool and what it can reach — statically extracted from the published source.
searchingests untrusted inputsearch_parallelingests untrusted inputextractno sensitive capabilityhealthno sensitive capabilityproject_memoryno sensitive capabilityproject_memory_searchno sensitive capabilityscholar_searchno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (7 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 8
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 |
|---|---|---|---|---|
v1.0.9 latest |
A 93/100 | 12 | 1.13.0 | 2026-09-07 |
v1.0.2 |
A 93/100 | 10 | 1.13.0 | 2026-09-01 |
v1.0.1 |
A 93/100 | 10 | 1.13.0 | 2026-08-31 |
v1.0.0 |
A 93/100 | 10 | 1.13.0 | 2026-08-30 |
v0.9.9 |
A 93/100 | 9 | 1.13.0 | 2026-08-28 |
Show 3 more versions ↓
v0.9.7 |
A 93/100 | 8 | 1.13.0 | 2026-08-27 |
v0.8.0 |
A 93/100 | 3 | 1.13.0 | 2026-08-25 |
v0.7.0 |
A 93/100 | 3 | 1.12.1 | 2026-08-10 |
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 google-surf-mcp --onlineMore in Web, Search & Scraping
Agent IP: MCP server with patents search tools
MCP server for searching the Agent Almanac — the public catalog of 9,000+ Model Context Protocol servers. Find, install, and discover MCP servers from inside Claude Desktop, Cursor, Continue, Zed, or any MCP-aware agent.
Search agents & MCP servers by capability, with daily-observed pricing, liveness and market data.
Verified merchants accepting agentic payments on Lightning/L402/BOLT12/USDT — search, verify, pay.
Airframe MCP Client - Connect agents to Airframe's product intelligence
Amazon product search demand over time, with growth for any keyword. Free key at trendsmcp.ai