Conductor (useconductor) MCP Server
@useconductor/conductor
npm
v2.2.0
Published by @useconductor — no publish provenance and no public repository, so the publisher could not be verified and the source cannot be independently located.
The AI Tool Hub — One MCP server. 255 tools. Every AI agent.
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 − 11 = 89. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −11 | Untrusted input concatenated into a command sink ×3 MTC-SRC-009 | injection |
2. Client adoption risk — 89 − 8 = 81. 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 |
| −2 | publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read |
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 23
high Shell/command execution in server code (dist/cli/commands/release.js)MTC-SRC-002
In the server's implementation (`dist/cli/commands/release.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: port { execFile } from 'child_process'; import { promisify } from 'util'; import { readFile, writeFile } from 'fs/promis
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/release.js
high Shell/command execution in server code (dist/dashboard/cli.js)MTC-SRC-002
In the server's implementation (`dist/dashboard/cli.js:2`): 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'; export async function dashboardCommand(conductor, opts) { const port = parse
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/dashboard/cli.js
high Shell/command execution in server code (dist/dashboard/server.js)MTC-SRC-002
In the server's implementation (`dist/dashboard/server.js:7`): 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: port { execFile } from 'child_process'; import { promisify } from 'util'; import rateLimit from 'express-rate-limit'; im
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/dashboard/server.js
high Shell/command execution in server code (dist/plugins/builtin/database.js)MTC-SRC-002
In the server's implementation (`dist/plugins/builtin/database.js:85`): 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: cFile } = await import('child_process'); const { promisify } = await import('util'); const execFileAsync
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/plugins/builtin/database.js
high Shell/command execution in server code (dist/plugins/builtin/docker.js)MTC-SRC-002
In the server's implementation (`dist/plugins/builtin/docker.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: port { execFile } from 'child_process'; import { promisify } from 'util'; import { existsSync } from 'fs'; const execFil
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/plugins/builtin/docker.js
high Shell/command execution in server code (dist/plugins/builtin/lumen.js)MTC-SRC-002
In the server's implementation (`dist/plugins/builtin/lumen.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: import { exec } from 'child_process'; import { promisify } from 'util'; import { readFile, writeFile, mkdir } from '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 dist/plugins/builtin/lumen.js
high Shell/command execution in server code (dist/plugins/builtin/shell.js)MTC-SRC-002
In the server's implementation (`dist/plugins/builtin/shell.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: port { execFile } from 'child_process'; import { promisify } from 'util'; import * as fs from 'fs/promises'; import * as
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/plugins/builtin/shell.js
high Shell/command execution in server code (dist/plugins/builtin/system.js)MTC-SRC-002
In the server's implementation (`dist/plugins/builtin/system.js:41`): 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: cSync } = await import('child_process'); try { if (os.platform() === 'win32'
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/plugins/builtin/system.js
high Shell/command execution in server code (dist/security/keychain.js)MTC-SRC-002
In the server's implementation (`dist/security/keychain.js:4`): 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: port { execSync } from 'child_process'; import path from 'path'; import os from 'os'; /** * Keychain — encrypted creden
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/security/keychain.js
medium Hardcoded egress to an external endpoint (dist/cli/commands/ai.js)MTC-SRC-003
In the server's implementation (`dist/cli/commands/ai.js:60`): 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 res = await fetch('https://openrouter.ai/api/v1/models', { headers: { Authorization: `Be
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/ai.js
medium Hardcoded egress to an external endpoint (dist/plugins/builtin/crypto.js)MTC-SRC-003
In the server's implementation (`dist/plugins/builtin/crypto.js:24`): 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 res = await fetch(`https://api.coingecko.com/api/v3/simple/price?ids=${encodeURIComponent(input.coin)}&vs_cu
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/plugins/builtin/crypto.js
medium Hardcoded egress to an external endpoint (dist/plugins/builtin/fun.js)MTC-SRC-003
In the server's implementation (`dist/plugins/builtin/fun.js:16`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const res = await fetch('https://official-joke-api.appspot.com/random_joke'); return await res
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/plugins/builtin/fun.js
medium Hardcoded egress to an external endpoint (dist/plugins/builtin/github.js)MTC-SRC-003
In the server's implementation (`dist/plugins/builtin/github.js:42`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const res = await fetch(`https://api.github.com${path}`, { method: options.method ?? 'GET',
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/plugins/builtin/github.js
medium Hardcoded egress to an external endpoint (dist/plugins/builtin/network.js)MTC-SRC-003
In the server's implementation (`dist/plugins/builtin/network.js:61`): 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 res = await fetch(`http://ip-api.com/json/${target}?fields=status,message,country,regionName,city,zip,lat,lo
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/plugins/builtin/network.js
medium Hardcoded egress to an external endpoint (dist/plugins/builtin/translate.js)MTC-SRC-003
In the server's implementation (`dist/plugins/builtin/translate.js:26`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const res = await fetch(`https://api.mymemory.translated.net/get?q=${encodeURIComponent(input.text)}&langpair=${en
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/plugins/builtin/translate.js
medium Hardcoded egress to an external endpoint (dist/plugins/builtin/weather.js)MTC-SRC-003
In the server's implementation (`dist/plugins/builtin/weather.js:10`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const res = await fetch(`https://geocoding-api.open-meteo.com/v1/search?name=${encodeURIComponent(city)}&count=1`)
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/plugins/builtin/weather.js
medium Hardcoded egress to an external endpoint (src/cli/commands/ai.ts)MTC-SRC-003
In the server's implementation (`src/cli/commands/ai.ts:67`): 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 res = await fetch('https://openrouter.ai/api/v1/models', { headers: { Authorization: `Bearer ${api
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/cli/commands/ai.ts
medium Hardcoded egress to an external endpoint (src/plugins/builtin/crypto.ts)MTC-SRC-003
In the server's implementation (`src/plugins/builtin/crypto.ts:29`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const res = await fetch( `https://api.coingecko.com/api/v3/simple/price?ids=${encodeURIComponent(input
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 src/plugins/builtin/crypto.ts
medium Hardcoded egress to an external endpoint (src/plugins/builtin/fun.ts)MTC-SRC-003
In the server's implementation (`src/plugins/builtin/fun.ts:21`): 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 res = await fetch('https://official-joke-api.appspot.com/random_joke'); return await res.json();
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 src/plugins/builtin/fun.ts
medium Untrusted input concatenated into a command sink (dist/dashboard/cli.js)MTC-SRC-009
In the server's implementation (`dist/dashboard/cli.js:18`): 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: 'xdg-open'; exec(`${opener} ${url}`, () => { /* ignore errors */ }); }
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/dashboard/cli.js
medium Untrusted input concatenated into a command sink (src/dashboard/cli.ts)MTC-SRC-009
In the server's implementation (`src/dashboard/cli.ts:25`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt' : 'xdg-open'; exec(`${opener} ${url}`, () => { /* ignore errors */ }); } // Keep alive
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 src/dashboard/cli.ts
medium Untrusted input concatenated into a command sink (test-all.mjs)MTC-SRC-009
In the server's implementation (`test-all.mjs:98`): 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: ion cli(cmd) { return execSync(`node ${join(__dir, 'dist/cli/index.js')} ${cmd}`, { encoding: 'utf8', timeout:
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 test-all.mjs
low Shell/command execution in packaging/dev tooling (dist/cli/commands/install.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/cli/commands/install.js:351`): 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: cSync } = await import('child_process'); execSync('npm --version', { stdio: 'pipe' }); } catch {
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/install.js
Tools 6
Each tool and what it can reach — statically extracted from the published source.
conductor_audit_queryno sensitive capabilityconductor_healthno sensitive capabilityconductor_metricsno sensitive capabilityconductor_statusno sensitive capabilityconductor_tools_listno sensitive capabilityconductor_webhooks_listno 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 |
|---|---|---|---|---|
v2.2.0 latest |
B 81/100 | 23 | 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 @useconductor/conductor --onlineOther implementations of Conductor 4
Independent packages implementing the same tool, scanned with the same engine. Compare all 5 side by side →
MCP server for exposing conductor endpoints.
MCP server for AI-assisted E2E test authoring with the Conductor framework
MCP server that orchestrates code execution in a sandboxed Deno environment with access to all MCP servers
A Node.js testing library for Model Context Protocol (MCP) servers
More 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