Agency MCP Server
agency-mcp-server
npm
v0.3.1
Source verified
Published by npupko — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
MCP server for on-demand agent template registry — search, browse, and spawn specialized AI agents
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 − 10 = 84. 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 |
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 2
high Shell/command execution in server code (dist/index.js)MTC-SRC-002
In the server's implementation (`dist/index.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: { execSync } from "node:child_process"; import { existsSync, mkdirSync, readFileSync, statSync, writeFileSync, } from "n
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/index.js
medium Untrusted input concatenated into a command sink (dist/index.js)MTC-SRC-009
In the server's implementation (`dist/index.js:77`): 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: e }); try { execSync(`git clone --depth 1 ${REPO_URL} ${DEFAULT_AGENTS_PATH}`, { stdio: "ignore"
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/index.js
Tools 4
Each tool and what it can reach — statically extracted from the published source.
agency_browseingests untrusted inputagency_searchno sensitive capabilityagency_statusno sensitive capabilityagency_updateno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (4 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 |
|---|---|---|---|---|
v0.3.1 latest |
B 84/100 | 2 | 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 agency-mcp-server --onlineMore in Gaming & Entertainment
Uncensored AI tools (chat, image, RE/malware analysis, JS deobfuscation, multi-step research) for Claude Desktop, Cursor, Cline, Zed, and any MCP client.
儿童故事 MCP 服务 - 提供故事列表和搜索功能
Grade any bet against thousands of play-by-play game simulations: win probability, odds, edge.
World Cup MCP server for the 2026 men's football tournament — live scores, fixtures, standings, read-only prediction-market signals, and paste-ready match cards. Works with Claude Code, Cursor, Codex, Windsurf, Zed. Not affiliated with FIFA or Anthropic.
MCP server exposing a live Dwarf Fortress fort to an AI agent as curated, semantic tools
MCP Server for Arknights: Endfield (TypeScript / stdio + Streamable HTTP)