Portel Ncp MCP Server
@portel/ncp
npm
v2.3.1
Published by @portel — 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.
Natural Context Provider (NCP) - 1 MCP to rule them all. Your MCPs, supercharged. Find any tool instantly, load on demand, run on schedule, ready for any client. Smart loading saves tokens and energy.
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 − 12.9 = 87. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −11.7 | Untrusted input concatenated into a command sink ×4 MTC-SRC-009 | injection |
| −1.2 | Package runs install-time scripts MTC-SUP-010 | supply-chain |
2. Client adoption risk — 87 − 7 = 80. 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 21
high Dynamic code execution in server code (dist/code-mode/validation/code-analyzer.js)MTC-SRC-001
In the server's implementation (`dist/code-mode/validation/code-analyzer.js:356`): 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: description: 'Direct eval() call - arbitrary code execution', }); dangerousConstructs.push('e
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/code-mode/validation/code-analyzer.js
high Shell/command execution in server code (dist/auth/mcp-oauth-provider.js)MTC-SRC-002
In the server's implementation (`dist/auth/mcp-oauth-provider.js:261`): 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: exec } = await import('child_process'); const { promisify } = await import('util'); const execA
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/auth/mcp-oauth-provider.js
high Shell/command execution in server code (dist/auth/oauth-auth-code-flow.js)MTC-SRC-002
In the server's implementation (`dist/auth/oauth-auth-code-flow.js:146`): 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: -open'; import('child_process').then(({ exec }) => { exec(`${start} "${url}"`, (error) => {
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/auth/oauth-auth-code-flow.js
high Shell/command execution in server code (dist/cli/commands/doctor.js)MTC-SRC-002
In the server's implementation (`dist/cli/commands/doctor.js:68`): 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'); const npmVersion = execSync('npm --version', { encoding: 'utf-8' })
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/commands/doctor.js
high Shell/command execution in server code (dist/cli/index.js)MTC-SRC-002
In the server's implementation (`dist/cli/index.js:566`): 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: exec } = await import('child_process'); const { promisify } = await import('util'); const execAsync = 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 dist/cli/index.js
high Shell/command execution in server code (dist/code-mode/code-worker.js)MTC-SRC-002
In the server's implementation (`dist/code-mode/code-worker.js:155`): 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: }, { pattern: /child_process/g, name: 'child_process access' }, // NOTE: fs. is now ALLOWED - we inject
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/code-mode/code-worker.js
high Shell/command execution in server code (dist/code-mode/package-approval.js)MTC-SRC-002
In the server's implementation (`dist/code-mode/package-approval.js:39`): 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: ew Set([ 'fs', 'child_process', 'cluster', 'net', 'dgram', 'dns', 'tls', 'vm', 'work
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/code-mode/package-approval.js
high Shell/command execution in server code (dist/code-mode/sandbox/subprocess-sandbox.js)MTC-SRC-002
In the server's implementation (`dist/code-mode/sandbox/subprocess-sandbox.js:12`): 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: import { spawn } from 'child_process'; import { join, dirname } from 'path'; import { fileURLToPath } from 'url'; impor
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/code-mode/sandbox/subprocess-sandbox.js
high Shell/command execution in server code (dist/code-mode/validation/code-analyzer.js)MTC-SRC-002
In the server's implementation (`dist/code-mode/validation/code-analyzer.js:87`): 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: ew Set([ 'fs', 'child_process', 'cluster', 'dgram', 'dns', 'net', 'tls', 'vm', 'work
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/code-mode/validation/code-analyzer.js
high Shell/command execution in server code (dist/internal-mcps/intelligence.photon.js)MTC-SRC-002
In the server's implementation (`dist/internal-mcps/intelligence.photon.js:10`): 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: ; import { exec } from 'child_process'; import { promisify } from 'util'; import { logger } from '../utils/logger.js'; 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 dist/internal-mcps/intelligence.photon.js
high Shell/command execution in server code (dist/internal-mcps/shell.photon.js)MTC-SRC-002
In the server's implementation (`dist/internal-mcps/shell.photon.js:10`): 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: / import { exec } from 'child_process'; import { promisify } from 'util'; const execAsync = promisify(exec); export defa
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/internal-mcps/shell.photon.js
medium Hardcoded egress to an external endpoint (dist/utils/mcp-update-checker.js)MTC-SRC-003
In the server's implementation (`dist/utils/mcp-update-checker.js:59`): 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://registry.npmjs.org/${packageName}/latest`, { signal: controll
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/utils/mcp-update-checker.js
medium Hardcoded egress to an external endpoint (dist/utils/update-checker.js)MTC-SRC-003
In the server's implementation (`dist/utils/update-checker.js:50`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const response = await fetch(`https://registry.npmjs.org/${this.packageName}/latest`, { signal: control
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/utils/update-checker.js
medium Hardcoded egress to an external endpoint (dist/utils/updater.js)MTC-SRC-003
In the server's implementation (`dist/utils/updater.js:26`): 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://registry.npmjs.org/${this.packageName}/latest`, { signal: control
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/utils/updater.js
medium Untrusted input concatenated into a command sink (dist/auth/oauth-auth-code-flow.js)MTC-SRC-009
In the server's implementation (`dist/auth/oauth-auth-code-flow.js:147`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: xec }) => { exec(`${start} "${url}"`, (error) => { if (error) { logger.d
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/auth/oauth-auth-code-flow.js
medium Untrusted input concatenated into a command sink (dist/cli/index.js)MTC-SRC-009
In the server's implementation (`dist/cli/index.js:2545`): 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: execSync(`which ${ed}`, { stdio: 'ignore' }); editorCmd = ed;
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/cli/index.js
medium Untrusted input concatenated into a command sink (dist/services/scheduler/launchd-manager.js)MTC-SRC-009
In the server's implementation (`dist/services/scheduler/launchd-manager.js:204`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try { execSync(`launchctl load "${plistPath}"`, { stdio: '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/services/scheduler/launchd-manager.js
medium Untrusted input concatenated into a command sink (dist/services/scheduler/task-scheduler-manager.js)MTC-SRC-009
In the server's implementation (`dist/services/scheduler/task-scheduler-manager.js:212`): 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: try { execSync(`schtasks /Delete /TN "${taskName}" /F`, { stdio: 'pipe' }); logger.debug(`
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/services/scheduler/task-scheduler-manager.js
medium Dynamic module load from a non-literal (dist/code-mode/code-worker.js)MTC-SRC-005
In the server's implementation (`dist/code-mode/code-worker.js:62`): 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: ckages.set(packageName, require(packageName)); } catch (e) { // Package not inst
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/code-mode/code-worker.js
medium Dynamic module load from a non-literal (dist/internal-mcps/photon-loader.js)MTC-SRC-005
In the server's implementation (`dist/internal-mcps/photon-loader.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: module = await import(cachedJsUrl); } else { // Regular JavaScript impo
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/internal-mcps/photon-loader.js
low Package runs install-time scripts (postinstall)MTC-SUP-010
"@portel/ncp" 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: npm run build:if-dev
Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.
Location: package @portel/ncp
Tools 6
Each tool and what it can reach — statically extracted from the published source.
codenetwork egressfindno sensitive capabilityLast Auto-Import Summaryno sensitive capabilityMCP Health Dashboardno sensitive capabilityNCP Getting Started Guideno sensitive capabilityrunno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (6 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 |
|---|---|---|---|---|
v2.3.1 latest |
B 80/100 | 21 | 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 @portel/ncp --onlineOther implementations of Portel Ncp 1
Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →
More 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