Arc Security MCP Server
arc-security-mcp
npm
v0.5.1
Published by arcself — 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.
AI agent security: scan skills for 25 attack classes + runtime monitoring (EDR for AI agents). Real-time scanning, behavioral anomaly detection, session monitoring, exfiltration alerts. 1,316+ findings from 450+ audits. OWASP Agentic AI Top 10 mapped.
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 − 6.3 = 94. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −6.3 | Untrusted input concatenated into a command sink MTC-SRC-009 | injection |
2. Client adoption risk — 94 − 11 = 83. 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 5
high Reads a sensitive credential path or dumps the environment (server.py)MTC-SRC-006
In the server's implementation (`server.py:2687`): 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: "wallet", r"\.gnupg", r"id_rsa", r"id_ed25519", r"\.openai_key", r"\.openrouter_key", r"\.resend_key", r"\.deepseek_
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 server.py
high Dynamic code execution in server code (server.py)MTC-SRC-001
In the server's implementation (`server.py:1668`): 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: amic code execution via eval(), Function(), or exec() that could execute injected code.", "regex": r"(eval\s*\(|
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 server.py
high Shell/command execution in server code (bin/arc-security-mcp.js)MTC-SRC-002
In the server's implementation (`bin/arc-security-mcp.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: , execSync } = require("child_process"); const path = require("path"); const fs = require("fs"); const serverPy = path.
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 bin/arc-security-mcp.js
high Shell/command execution in server code (server.py)MTC-SRC-002
In the server's implementation (`server.py:369`): 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: "Unrestricted child_process.exec() — executes ANY shell command with zero sanitization", "No allow
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 server.py
medium Untrusted input concatenated into a command sink (bin/arc-security-mcp.js)MTC-SRC-009
In the server's implementation (`bin/arc-security-mcp.js:23`): 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: mand(cmd) { try { execSync(`which ${cmd}`, { stdio: "ignore" }); return true; } catch { return false;
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 bin/arc-security-mcp.js
Tools 14
Each tool and what it can reach — statically extracted from the published source.
scan_skill_realtimeingests untrusted inputanalyze_skill_codeno sensitive capabilityanalyze_skill_intentno sensitive capabilitycheck_skill_safetyno sensitive capabilityget_attack_class_infono sensitive capabilityget_owasp_mappingno sensitive capabilityget_session_alertsno sensitive capabilityget_threat_landscapeno sensitive capabilitylist_dangerous_patternsno sensitive capabilitymonitor_endno sensitive capability
Show 4 more tools ↓
monitor_eventno sensitive capabilitymonitor_startno sensitive capabilitysecurity_checklistno sensitive capabilityset_monitor_policyno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (14 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 |
|---|---|---|---|---|
v0.5.1 latest |
B 83/100 | 5 | 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 arc-security-mcp --onlineMore in Analytics & Monitoring
Public-safe MCP admin discovery contract descriptors and response builders.
Pokemon Champions battle advisor MCP server
Airflow MCP server — DAG list, runs, task instances, log tails, trigger and clear over the Airflow REST API
MCP analytics wrapper SDK that instruments MCP tool declarations with telemetry.
AI-ready GIS, geofencing, DataSynch, CRM, inventory, routing, APIs, telemetry and workflows.
AI-native social listening. Monitor buying signals and run GTM workflows via natural language.