Ada Mcp MCP Server
@ada-mcp/mcp-server
npm
v0.1.87
Published by @ada-mcp — 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.
ADA MCP server for web/mobile automation (stdio + remote HTTP)
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 − 1.2 = 99. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −1.2 | Package runs install-time scripts MTC-SUP-010 | supply-chain |
2. Client adoption risk — 99 − 7 = 92. 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 8
high Dynamic code execution in server code (dist/cli.cjs)MTC-SRC-001
In the server's implementation (`dist/cli.cjs:28694`): 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 makeValidate = new Function(`${names_1.default.self}`, `${names_1.default.scope}`, sourceCode); const v
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 dist/cli.cjs
high Shell/command execution in server code (dist/cli.cjs)MTC-SRC-002
In the server's implementation (`dist/cli.cjs:935`): 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: child = (0, import_node_child_process.spawn)(cmd, ["list", "targets"], { stdio: ["ignore", "pipe", "pipe"],
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 dist/cli.cjs
high Shell/command execution in server code (plugins/driver-android.cjs)MTC-SRC-002
In the server's implementation (`plugins/driver-android.cjs:529`): 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: child = (0, import_node_child_process2.spawn)("adb", adbArgs, { stdio: pipeStdout ? ["ignore", "pipe", "pipe"] : [
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 plugins/driver-android.cjs
high Shell/command execution in server code (plugins/driver-harmony.cjs)MTC-SRC-002
In the server's implementation (`plugins/driver-harmony.cjs:1529`): 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: text.ts var import_node_child_process = require("node:child_process"); var HARMONY_PASTE_KEY_EVENT = "uitest uiInput key
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 plugins/driver-harmony.cjs
high Shell/command execution in server code (plugins/driver-ios.cjs)MTC-SRC-002
In the server's implementation (`plugins/driver-ios.cjs:88`): 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: child = (0, import_node_child_process.spawn)(command, args, { stdio: ["ignore", "pipe", "pipe"], shell: proc
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 plugins/driver-ios.cjs
high Shell/command execution in server code (plugins/driver-playwright.cjs)MTC-SRC-002
In the server's implementation (`plugins/driver-playwright.cjs:482`): 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: unch.ts var import_node_child_process = require("node:child_process"); var import_node_fs = __toESM(require("node:fs"),
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 plugins/driver-playwright.cjs
low Reads a sensitive credential path or dumps the environment in packaging/dev tooling (scripts/preinstall-probes.mjs)MTC-SRC-006
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/preinstall-probes.mjs:44`): 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: cPath = path.join(root, ".npmrc"); const regLine = `registry=${registry}\n`; let npmrc = ""; try { npmrc = fs.
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 scripts/preinstall-probes.mjs
low Package runs install-time scripts (preinstall)MTC-SUP-010
"@ada-mcp/mcp-server" executes preinstall 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 scripts/preinstall-probes.mjs
Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.
Location: package @ada-mcp/mcp-server
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, 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 |
|---|---|---|---|---|
v0.1.87 latest |
A 92/100 | 8 | 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 @ada-mcp/mcp-server --onlineMore in Browser Automation
Model Context Protocol (MCP) server that integrates AgentQL data extraction capabilities.
Screenshot any URL or HTML as PNG/JPEG/WebP from your AI agent. Full-page, clean, no install.
MCP server for aria51 accessibility scanner
Bridge any browser web app to Claude Code via MCP
Browserbase’s official MCP server: cloud headless browsers for agents, with sessions and screenshots.
MCP server for AI web browser automation using Browserbase and Stagehand