Agent Cards MCP Server
agent-cards
npm
v0.7.4
Published by tiny-agent-company — 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.
CLI for managing virtual debit cards for 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 − 7 = 87. 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 |
| −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 9
high Shell/command execution in server code (dist/src/commands/setup-mcp.js)MTC-SRC-002
In the server's implementation (`dist/src/commands/setup-mcp.js:3`): 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: { execFileSync } from 'child_process'; import { getMcpUrl } from '../lib/config.js'; /** * Register the Agentcard MCP
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/commands/setup-mcp.js
high Shell/command execution in server code (dist/src/companies/lib/wizard/detect.js)MTC-SRC-002
In the server's implementation (`dist/src/companies/lib/wizard/detect.js:3`): 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'; const FRAMEWORK_MARKERS = [ ['next', 'Next.js'], ['express', 'Express'],
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/companies/lib/wizard/detect.js
high Shell/command execution in server code (dist/src/engineer/adapters/codex.js)MTC-SRC-002
In the server's implementation (`dist/src/engineer/adapters/codex.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: ort { spawnSync } from 'child_process'; import { boundSummary } from './types.js'; /** True when a `codex` binary answer
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/engineer/adapters/codex.js
high Shell/command execution in server code (dist/src/engineer/adapters/paste.js)MTC-SRC-002
In the server's implementation (`dist/src/engineer/adapters/paste.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 { spawn } from 'child_process'; import chalk from 'chalk'; /** Platform clipboard commands, first hit wins. Expo
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/engineer/adapters/paste.js
high Shell/command execution in server code (dist/src/engineer/commands/connect.js)MTC-SRC-002
In the server's implementation (`dist/src/engineer/commands/connect.js:3`): 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 { spawn } from 'child_process'; import { openSync, writeFileSync, rmSync, existsSync, readFileSync } 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/src/engineer/commands/connect.js
high Shell/command execution in server code (dist/src/lib/global-install.js)MTC-SRC-002
In the server's implementation (`dist/src/lib/global-install.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 { execSync } from 'child_process'; import { delimiter } from 'path'; import chalk from 'chalk'; import inquirer 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/lib/global-install.js
high Shell/command execution in server code (dist/src/lib/update.js)MTC-SRC-002
In the server's implementation (`dist/src/lib/update.js:3`): 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: c, execFileSync } from 'child_process'; import { CONFIG_DIR } from './config.js'; const VERSION_CACHE_FILE = join(CONFIG
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/lib/update.js
medium Hardcoded egress to an external endpoint (dist/src/lib/update.js)MTC-SRC-003
In the server's implementation (`dist/src/lib/update.js:74`): 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://registry.npmjs.org/agent-cards/latest', { signal: AbortSignal.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 dist/src/lib/update.js
medium Untrusted input concatenated into a command sink (dist/src/companies/lib/wizard/detect.js)MTC-SRC-009
In the server's implementation (`dist/src/companies/lib/wizard/detect.js:33`): 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: erns.join('|'); execSync(`rg -li --max-count 1 -m 1 ${JSON.stringify(alt)} -g '!node_modules' -g '!.git' .`, {
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/companies/lib/wizard/detect.js
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Versions 10
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 |
|---|---|---|---|---|
v0.7.4 latest |
B 87/100 | 9 | 1.13.0 | 2026-09-07 |
v0.6.28 |
B 86/100 | 6 | 1.12.1 | 2026-08-09 |
v0.6.26 |
B 86/100 | 6 | 1.12.1 | 2026-08-07 |
v0.6.24 |
B 86/100 | 6 | 1.12.1 | 2026-08-05 |
v0.6.23 |
B 86/100 | 6 | 1.12.1 | 2026-08-04 |
Show 5 more versions ↓
v0.6.21 |
B 86/100 | 6 | 1.12.1 | 2026-07-28 |
v0.6.20 |
B 86/100 | 6 | 1.12.1 | 2026-07-27 |
v0.6.19 |
B 86/100 | 6 | 1.12.1 | 2026-07-27 |
v0.6.18 |
B 86/100 | 6 | 1.9.0 | 2026-07-24 |
v0.6.16 |
B 86/100 | 6 | 1.9.0 | 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-cards --onlineMore in Business & CRM
Free public tax reference data — GST/VAT, income, company and capital-gains tax rules for 50+ countries.
The approval gate for unattended UCP buying agents — a policy/approval MCP proxy in front of a merchant's UCP checkout endpoint.
Autotask PSA MCP server. Generic entity query/get/create/update across the full REST API plus convenience tools for tickets, companies, contacts, projects, tasks and time entries. AI-safe with readonly mode and destructive-action confirmation. stdio + opt
MCP server for B2C Commerce developer experience tools
Search, compare and contact real-world companies through a public MCP business directory.
Norwegian business register (Brønnøysundregistrene) as an MCP server — companies, roles, subunits and annual accounts, with the register's silent traps encoded as guards.