Superbased MCP Server
superbased
npm
v2.0.9
Published by marmutapp — 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.
Screenshot capture, AI analysis, OCR, visual regression testing, token compression — headless server + MCP tools for AI coding CLIs
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 − 15.4 = 85. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −15.4 | Untrusted input concatenated into a command sink ×10 MTC-SRC-009 | injection |
2. Client adoption risk — 85 − 11 = 74. 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 32
high Reads a sensitive credential path or dumps the environment (dist/electron/modules/dictation.js)MTC-SRC-006
In the server's implementation (`dist/electron/modules/dictation.js:351`): 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: /\.\s*(?:npm ?rc)\b/gi, '.npmrc'], [/\.\s*(?:nvm ?rc)\b/gi, '.nvmrc'], [/\.\s*(?:e ?n ?v)\b/gi, '.env'],
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/electron/modules/dictation.js
high Reads a sensitive credential path or dumps the environment (dist/headless/electron/modules/dictation.js)MTC-SRC-006
In the server's implementation (`dist/headless/electron/modules/dictation.js:351`): 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: /\.\s*(?:npm ?rc)\b/gi, '.npmrc'], [/\.\s*(?:nvm ?rc)\b/gi, '.nvmrc'], [/\.\s*(?:e ?n ?v)\b/gi, '.env'],
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/headless/electron/modules/dictation.js
high Shell/command execution in server code (dist/electron/core/input-injection/windows.js)MTC-SRC-002
In the server's implementation (`dist/electron/core/input-injection/windows.js:47`): 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: = __importStar(require("child_process")); const logger_1 = __importDefault(require("../../logger")); // Inline C# using
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/electron/core/input-injection/windows.js
high Shell/command execution in server code (dist/electron/main.js)MTC-SRC-002
In the server's implementation (`dist/electron/main.js:1971`): 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: { execSync } = require('child_process'); if (process.platform === 'darwin') { execSync(`osas
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/electron/main.js
high Shell/command execution in server code (dist/electron/modules/context-menu-detect.js)MTC-SRC-002
In the server's implementation (`dist/electron/modules/context-menu-detect.js:59`): 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: = __importStar(require("child_process")); const fs = __importStar(require("fs")); const os = __importStar(require("os"))
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/electron/modules/context-menu-detect.js
high Shell/command execution in server code (dist/electron/modules/platform/dpi.js)MTC-SRC-002
In the server's implementation (`dist/electron/modules/platform/dpi.js:32`): 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 } = require('child_process'); const out = execFileSync('reg', ['query', 'HKCU\\Control Panel\\Des
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/electron/modules/platform/dpi.js
high Shell/command execution in server code (dist/electron/modules/platform/macos/ax.js)MTC-SRC-002
In the server's implementation (`dist/electron/modules/platform/macos/ax.js:13`): 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: Adapter = void 0; const child_process_1 = require("child_process"); const errors_1 = require("../errors"); const shared_
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/electron/modules/platform/macos/ax.js
high Shell/command execution in server code (dist/electron/modules/platform/macos/capture.js)MTC-SRC-002
In the server's implementation (`dist/electron/modules/platform/macos/capture.js:13`): 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: Adapter = void 0; const child_process_1 = require("child_process"); const shared_1 = require("../shared"); const capture
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/electron/modules/platform/macos/capture.js
high Shell/command execution in server code (dist/electron/modules/platform/macos/launch.js)MTC-SRC-002
In the server's implementation (`dist/electron/modules/platform/macos/launch.js:19`): 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: Adapter = void 0; const child_process_1 = require("child_process"); const errors_1 = require("../errors"); const shared_
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/electron/modules/platform/macos/launch.js
high Shell/command execution in server code (dist/electron/modules/platform/macos/window.js)MTC-SRC-002
In the server's implementation (`dist/electron/modules/platform/macos/window.js:26`): 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: Adapter = void 0; const child_process_1 = require("child_process"); const errors_1 = require("../errors"); const shared_
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/electron/modules/platform/macos/window.js
high Shell/command execution in server code (dist/electron/modules/platform/shared.js)MTC-SRC-002
In the server's implementation (`dist/electron/modules/platform/shared.js:110`): 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: childProcess = require('child_process'); const script = pathMod.join(os.tmpdir(), `superbased-displays-${Date.no
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/electron/modules/platform/shared.js
high Shell/command execution in server code (dist/electron/modules/platform/windows/ax.js)MTC-SRC-002
In the server's implementation (`dist/electron/modules/platform/windows/ax.js:44`): 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: = __importStar(require("child_process")); const fs = __importStar(require("fs")); const os = __importStar(require("os"))
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/electron/modules/platform/windows/ax.js
medium Hardcoded egress to an external endpoint (dist/electron/modules/dictation.js)MTC-SRC-003
In the server's implementation (`dist/electron/modules/dictation.js:172`): 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 resp = await fetch('https://api.superbased.app/api/v1/ai/dictation-stt-config', { headers: { 'Aut
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/electron/modules/dictation.js
medium Hardcoded egress to an external endpoint (dist/headless/electron/modules/dictation.js)MTC-SRC-003
In the server's implementation (`dist/headless/electron/modules/dictation.js:172`): 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 resp = await fetch('https://api.superbased.app/api/v1/ai/dictation-stt-config', { headers: { 'Aut
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/headless/electron/modules/dictation.js
medium Hardcoded egress to an external endpoint (dist/headless/headless/dictation-hotkey.js)MTC-SRC-003
In the server's implementation (`dist/headless/headless/dictation-hotkey.js:172`): 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 resp = await fetch('https://api.superbased.app/api/v1/ai/dictation-stt-config', { headers: { 'Aut
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/headless/headless/dictation-hotkey.js
medium Untrusted input concatenated into a command sink (dist/electron/main.js)MTC-SRC-009
In the server's implementation (`dist/electron/main.js:2098`): 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: cript); execSync(`osascript "${tmpScpt}"`); try { fs.unlinkSync(tmpS
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/electron/main.js
medium Untrusted input concatenated into a command sink (dist/electron/modules/context-menu-detect.js)MTC-SRC-009
In the server's implementation (`dist/electron/modules/context-menu-detect.js:102`): 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: onst out = childProcess.execSync(`powershell -ExecutionPolicy Bypass -File "${script}"`, { encoding: 'utf-8', timeout: 5
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/electron/modules/context-menu-detect.js
medium Untrusted input concatenated into a command sink (dist/electron/modules/platform/shared.js)MTC-SRC-009
In the server's implementation (`dist/electron/modules/platform/shared.js:128`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: out = childProcess.execSync(`powershell -ExecutionPolicy Bypass -File "${script}"`, { encoding: 'utf-8', timeout: 5
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/electron/modules/platform/shared.js
medium Untrusted input concatenated into a command sink (dist/electron/modules/platform/windows/session.js)MTC-SRC-009
In the server's implementation (`dist/electron/modules/platform/windows/session.js:49`): 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: onst out = childProcess.execSync(`powershell -NoProfile -Command "@(Get-Process -Name '${name}' -ErrorAction SilentlyCon
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/electron/modules/platform/windows/session.js
medium Untrusted input concatenated into a command sink (dist/electron/modules/platform/windows/window.js)MTC-SRC-009
In the server's implementation (`dist/electron/modules/platform/windows/window.js:210`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: onst out = childProcess.execSync(`powershell -ExecutionPolicy Bypass -File "${script}" -Hwnd ${nativeId} -State ${state}
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/electron/modules/platform/windows/window.js
medium Untrusted input concatenated into a command sink (dist/electron/modules/window-activate.js)MTC-SRC-009
In the server's implementation (`dist/electron/modules/window-activate.js:209`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { childProcess.execSync(`powershell -ExecutionPolicy Bypass -File "${script}" -TargetHwnd ${targetHwnd}`, { tim
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/electron/modules/window-activate.js
medium Untrusted input concatenated into a command sink (dist/electron/modules/window-input.js)MTC-SRC-009
In the server's implementation (`dist/electron/modules/window-input.js:121`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { childProcess.execSync(`powershell -ExecutionPolicy Bypass -File "${script}" -Hwnd ${hwnd}`, { timeout: 3000,
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/electron/modules/window-input.js
medium Untrusted input concatenated into a command sink (dist/headless/electron/modules/context-menu-detect.js)MTC-SRC-009
In the server's implementation (`dist/headless/electron/modules/context-menu-detect.js:102`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: onst out = childProcess.execSync(`powershell -ExecutionPolicy Bypass -File "${script}"`, { encoding: 'utf-8', timeout: 5
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/headless/electron/modules/context-menu-detect.js
medium Untrusted input concatenated into a command sink (dist/headless/electron/modules/platform/shared.js)MTC-SRC-009
In the server's implementation (`dist/headless/electron/modules/platform/shared.js:128`): 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: out = childProcess.execSync(`powershell -ExecutionPolicy Bypass -File "${script}"`, { encoding: 'utf-8', timeout: 5
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/headless/electron/modules/platform/shared.js
medium Untrusted input concatenated into a command sink (dist/headless/electron/modules/platform/windows/session.js)MTC-SRC-009
In the server's implementation (`dist/headless/electron/modules/platform/windows/session.js:49`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: onst out = childProcess.execSync(`powershell -NoProfile -Command "@(Get-Process -Name '${name}' -ErrorAction SilentlyCon
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/headless/electron/modules/platform/windows/session.js
medium Dynamic module load from a non-literal (dist/electron/core/config.js)MTC-SRC-005
In the server's implementation (`dist/electron/core/config.js:58`): 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 pkg = require(p); if (pkg.version) { cachedVersion = pkg.version;
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/electron/core/config.js
medium Dynamic module load from a non-literal (dist/electron/modules/api-server.js)MTC-SRC-005
In the server's implementation (`dist/electron/modules/api-server.js:2628`): 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: mod = require(p); break; } }
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/electron/modules/api-server.js
medium Dynamic module load from a non-literal (dist/headless/electron/core/config.js)MTC-SRC-005
In the server's implementation (`dist/headless/electron/core/config.js:58`): 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 pkg = require(p); if (pkg.version) { cachedVersion = pkg.version;
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/headless/electron/core/config.js
medium Dynamic module load from a non-literal (dist/headless/electron/modules/api-server.js)MTC-SRC-005
In the server's implementation (`dist/headless/electron/modules/api-server.js:2628`): 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: mod = require(p); break; } }
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/headless/electron/modules/api-server.js
medium Dynamic module load from a non-literal (dist/headless/headless/cli.js)MTC-SRC-005
In the server's implementation (`dist/headless/headless/cli.js:157`): 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: st { startMcpServer } = require(mcpPath); await startMcpServer(47592, process.cwd()); } async function handleAuth(su
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/headless/headless/cli.js
medium Dynamic module load from a non-literal (dist/headless/headless/doctor.js)MTC-SRC-005
In the server's implementation (`dist/headless/headless/doctor.js:175`): 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: me) { try { require(name); return { label: `Native module: ${name}`, status: 'green', detail: 'loada
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/headless/headless/doctor.js
medium Dynamic module load from a non-literal (dist/headless/headless/tui-bridge.js)MTC-SRC-005
In the server's implementation (`dist/headless/headless/tui-bridge.js:75`): 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: .then(s => __importStar(require(s)))); if (entry === 'settings') await mod.startSettingsTui(); else
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/headless/headless/tui-bridge.js
Tools 72
Each tool and what it can reach — statically extracted from the published source.
superbased_galleryingests untrusted inputsuperbased_ui_dumpreads sensitive datasuperbased_accessibility_treeno sensitive capabilitysuperbased_aino sensitive capabilitysuperbased_ai_usageno sensitive capabilitysuperbased_annotateno sensitive capabilitysuperbased_authno sensitive capabilitysuperbased_ax_invokeno sensitive capabilitysuperbased_baselineno sensitive capabilitysuperbased_captureno sensitive capability
Show 62 more tools ↓
superbased_capture_imageno sensitive capabilitysuperbased_capture_templateno sensitive capabilitysuperbased_clickno sensitive capabilitysuperbased_clipboardno sensitive capabilitysuperbased_compress_textno sensitive capabilitysuperbased_context_menu_selectno sensitive capabilitysuperbased_describe_framesno sensitive capabilitysuperbased_dialog_handleno sensitive capabilitysuperbased_dictateno sensitive capabilitysuperbased_dictation_historyno sensitive capabilitysuperbased_diffno sensitive capabilitysuperbased_display_listno sensitive capabilitysuperbased_doctor_gui_automationno sensitive capabilitysuperbased_dragno sensitive capabilitysuperbased_drag_fileno sensitive capabilitysuperbased_dry_runno sensitive capabilitysuperbased_exportno sensitive capabilitysuperbased_find_imageno sensitive capabilitysuperbased_find_in_pageno sensitive capabilitysuperbased_find_title_bar_drag_regionno sensitive capabilitysuperbased_focus_windowno sensitive capabilitysuperbased_form_fillno sensitive capabilitysuperbased_gallery_imageno sensitive capabilitysuperbased_gallery_updateno sensitive capabilitysuperbased_healthno sensitive capabilitysuperbased_hotkeyno sensitive capabilitysuperbased_hoverno sensitive capabilitysuperbased_launch_appno sensitive capabilitysuperbased_licenseno sensitive capabilitysuperbased_locateno sensitive capabilitysuperbased_mouse_positionno sensitive capabilitysuperbased_narrateno sensitive capabilitysuperbased_ocrno sensitive capabilitysuperbased_open_urlno sensitive capabilitysuperbased_pixel_colorno sensitive capabilitysuperbased_presetsno sensitive capabilitysuperbased_projectno sensitive capabilitysuperbased_recordingno sensitive capabilitysuperbased_redactno sensitive capabilitysuperbased_replayno sensitive capabilitysuperbased_resize_windowno sensitive capabilitysuperbased_screenshotno sensitive capabilitysuperbased_scrollno sensitive capabilitysuperbased_scroll_captureno sensitive capabilitysuperbased_scroll_tono sensitive capabilitysuperbased_sequenceno sensitive capabilitysuperbased_sessionsno sensitive capabilitysuperbased_settingsno sensitive capabilitysuperbased_stt_statusno sensitive capabilitysuperbased_tab_managementno sensitive capabilitysuperbased_toolsno sensitive capabilitysuperbased_transcribeno sensitive capabilitysuperbased_tray_clickno sensitive capabilitysuperbased_typeno sensitive capabilitysuperbased_undo_lastno sensitive capabilitysuperbased_virtual_desktopno sensitive capabilitysuperbased_waitno sensitive capabilitysuperbased_wait_forno sensitive capabilitysuperbased_window_boundsno sensitive capabilitysuperbased_window_listno sensitive capabilitysuperbased_window_stateno sensitive capabilitysuperbased_workspace_syncno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (72 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 |
|---|---|---|---|---|
v2.0.9 latest |
C 74/100 | 32 | 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 superbased --onlineMore 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.