Agent Security (mdfifty50-boop) MCP Server
agent-security-mcp
npm
v0.1.3
Published by mdfifty50-boop — 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.
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 − 33 = 67. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −33 | Hardcoded AWS access key id in server code ×2 MTC-SRC-008 | exfiltration |
2. Client adoption risk — 67 − 1 = 66. 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 |
|---|---|
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Grade capped: 2 confirmed high findings → grade capped at D. A hard gate overrides the point total — no amount of clean surface buys back a confirmed catastrophe.
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 4
high Hardcoded AWS access key id in server code (src/__tests__/server.test.js)MTC-SRC-008
A live-looking AWS access key id is hardcoded in `src/__tests__/server.test.js:24`. Secrets in source ship to everyone who installs the package and are a direct credential leak.
Evidence: AWS access key id: AKIA…(redacted)
Fix: Remove the secret, rotate it, and load credentials from the environment or a secret store.
Location: server src/__tests__/server.test.js
high Hardcoded AWS access key id in server code (src/tools/secret-scanner.test.js)MTC-SRC-008
A live-looking AWS access key id is hardcoded in `src/tools/secret-scanner.test.js:22`. Secrets in source ship to everyone who installs the package and are a direct credential leak.
Evidence: AWS access key id: AKIA…(redacted)
Fix: Remove the secret, rotate it, and load credentials from the environment or a secret store.
Location: server src/tools/secret-scanner.test.js
low Shell/command execution in packaging/dev tooling (src/tools/prompt-injection.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`src/tools/prompt-injection.js:187`): 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: (|subprocess|os\.system|child_process|Runtime\.exec/i, severity: 'high', category: 'tool_manipulation', desc
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/tools/prompt-injection.js
low Shell/command execution in packaging/dev tooling (src/tools/tool-poisoning.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`src/tools/tool-poisoning.js:79`): 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: |eval|system|subprocess|child_process|spawn|shell|bash\s+-c|sh\s+-c)/i, severity: 'high', description: 'Tool 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 src/tools/tool-poisoning.js
Tools 8
Each tool and what it can reach — statically extracted from the published source.
audit_agent_permissionsno sensitive capabilitydetect_prompt_injectionno sensitive capabilitydetect_tool_poisoningno sensitive capabilitygenerate_security_reportno sensitive capabilityhealth_checkno sensitive capabilityscan_mcp_configno sensitive capabilityscan_secretsno sensitive capabilityvalidate_scope_contractno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (8 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 |
|---|---|---|---|---|
v0.1.3 latest |
D 66/100 | 4 | 1.8.0 | 2026-07-23 |
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 agent-security-mcp --onlineOther implementations of Agent Security 1
Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →
More in Developer Tools
Security scan results for the 1stay MCP server.
Security scan results for the Adguard Home MCP server.
Security scan results for the Ado Browser MCP server.
Security scan results for the Adobe Experience Dev MCP server.
Security scan results for the Aemet MCP server.
Security scan results for the Affinity Mcp Bridge MCP server.