Port Authority Agent Terminal MCP Server
port-authority-agent-terminal-mcp
npm
v0.4.3
Source verified
Published by charlesonogwu — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
Cross-platform (Windows + macOS) lane coordinator for AI coding agents (Claude, Codex, etc.) — keeps multiple local agents from colliding on dev-server ports, Chrome debug ports, and Chrome user profiles. Includes a CLI, an MCP server, and a native Tauri
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 − 6 = 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 |
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 14
high Tool "page_eval" exposes command/code executionMTC-CAP-001
Tool "page_eval" appears to run shell commands or evaluate code (keyword "eval" in tool name). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool page_eval
high Dynamic code execution in server code (dist/src/core/pagejs.js)MTC-SRC-001
In the server's implementation (`dist/src/core/pagejs.js:19`): 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: othing is executed. new Function(`return (${expr});`); return expr; } /** Page metadata: url, title, readyState.
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/src/core/pagejs.js
high Shell/command execution in server code (dist/src/cli/autostart.js)MTC-SRC-002
In the server's implementation (`dist/src/cli/autostart.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: rt { spawn } from "node:child_process"; import { access, rm } from "node:fs/promises"; import { dirname, join } from "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/src/cli/autostart.js
high Shell/command execution in server code (dist/src/cli/install-mcp.js)MTC-SRC-002
In the server's implementation (`dist/src/cli/install-mcp.js:21`): 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 { copyFile, mkdir, readFile, writeFile } from "node:fs/promises"; import
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/src/cli/install-mcp.js
high Shell/command execution in server code (dist/src/cli/shortcut.js)MTC-SRC-002
In the server's implementation (`dist/src/cli/shortcut.js:14`): 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 { access, copyFile, mkdir, rm } from "node:fs/promises"; import { homedir
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/src/cli/shortcut.js
high Shell/command execution in server code (dist/src/core/chrome.js)MTC-SRC-002
In the server's implementation (`dist/src/core/chrome.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 { existsSync } from "node:fs"; import { mkdir } from "node:fs/promises";
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/src/core/chrome.js
high Shell/command execution in server code (dist/src/core/firefox.js)MTC-SRC-002
In the server's implementation (`dist/src/core/firefox.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 { existsSync } from "node:fs"; import { mkdir } from "node:fs/promises";
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/src/core/firefox.js
high Shell/command execution in server code (dist/src/core/scanner.js)MTC-SRC-002
In the server's implementation (`dist/src/core/scanner.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 { isWindows } from "./paths.js"; function runCommand(cmd, args, opts = {}
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/src/core/scanner.js
high Shell/command execution in server code (dist/src/dashboard/focus.js)MTC-SRC-002
In the server's implementation (`dist/src/dashboard/focus.js:57`): 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 process from "node:process"; import { scanPorts } from "../core/scanner.j
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/src/dashboard/focus.js
high Shell/command execution in server code (dist/src/dashboard/kill.js)MTC-SRC-002
In the server's implementation (`dist/src/dashboard/kill.js: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: spawnSync } from "node:child_process"; import { setLaneStatus, listLanes } from "../core/registry.js"; import { scanPor
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/src/dashboard/kill.js
high Shell/command execution in server code (dist/src/dashboard/launch.js)MTC-SRC-002
In the server's implementation (`dist/src/dashboard/launch.js:25`): 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 { access } from "node:fs/promises"; import { dirname, join, resolve } 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 dist/src/dashboard/launch.js
high Shell/command execution in server code (dist/src/dashboard/process-info.js)MTC-SRC-002
In the server's implementation (`dist/src/dashboard/process-info.js:16`): 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 process from "node:process"; export const EMPTY_PROCESS_SNAPSHOT = {
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/src/dashboard/process-info.js
low Mutating tool "page_eval" declares no destructiveHintMTC-CAP-005
Tool "page_eval" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool page_eval
low Package runs install-time scripts (postinstall)MTC-SUP-010
"port-authority-agent-terminal-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 -e "try{require('./scripts/postinstall.cjs')}catch(e){if(e&&e.code==='MODULE_NOT_FOUND'&&String(e.message).includes('scripts/postinstall.cjs')){console.war
Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.
Location: package port-authority-agent-terminal-mcp
Tools 23
Each tool and what it can reach — statically extracted from the published source.
page_evalruns code / shelladopt_profileno sensitive capabilitycheck_laneno sensitive capabilityclose_browserno sensitive capabilitydoctorno sensitive capabilityfind_free_laneno sensitive capabilityfind_saved_loginno sensitive capabilitylaunch_browser_laneno sensitive capabilitylaunch_chrome_laneno sensitive capabilitylist_lanesno sensitive capability
Show 13 more tools ↓
openno sensitive capabilitypage_clickno sensitive capabilitypage_fillno sensitive capabilitypage_gotono sensitive capabilitypage_newtabno sensitive capabilitypage_screenshotno sensitive capabilitypage_tabsno sensitive capabilitypage_textno sensitive capabilityrelease_laneno sensitive capabilityremember_loginno sensitive capabilityremember_profileno sensitive capabilityreserve_laneno sensitive capabilityscan_portsno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (23 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 4
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 |
|---|---|---|---|---|
v0.4.3 latest |
A 93/100 | 14 | 1.13.0 | 2026-09-07 |
v0.4.2 |
A 93/100 | 14 | 1.13.0 | 2026-09-05 |
v0.4.1 |
A 92/100 | 14 | 1.13.0 | 2026-09-04 |
v0.4.0 |
A 92/100 | 14 | 1.13.0 | 2026-09-01 |
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 port-authority-agent-terminal-mcp --onlineMore in AI & Agents
Authenticated MCP transport with HTTP Signatures for AAuth agents
Local-first MCP server for parallel AI coding agents to claim file ownership before edits, preventing stomping on each other in the same worktree.
Agent-agnostic intercommunication system — sessions, messaging, channels, shared state, and real-time events
MCP server for AI agent task communication and delegation with diagnostic lifecycle visibility
Programmatic add/link/unlink for MCP servers across 23 AI coding agents (Claude Code, Claude Desktop, Cursor, VS Code, Codex, Gemini CLI, Zed, Cline, OpenCode, Goose, Kiro, Windsurf, and more). Functional API with dry-run support.
MCP server layer exposing agent-mesh orchestrator as an MCP agent