io.github.vpatser1/mcp-server-security-scanner
NPM · MCP-SERVER-SECURITY-SCANNER · SCANNED AUG 7
Scan MCP configs for 30+ CVEs, prompt injection, tool poisoning; validate OAuth configs
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score →
Supply Chain Security87
- No malware found by supply-chain analysis.Pass
- Known CVEs were checked across the 95 of 99 dependencies we could resolve, so this covers what we could see, not the whole tree.Partial
- No install/post-install scripts declared.Pass
- Dependency health was assessed across the 95 of 99 dependencies we could resolve, so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency19
- Repository check failed: no source repository is declared. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 2 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability77
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 483 tokens (~96/item across 5 items; 5 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.
npm · mcp-server-security-scanner
claude mcp add vpatser1-mcp-server-security-scanner -- npx -y mcp-server-security-scanner
codex mcp add vpatser1-mcp-server-security-scanner -- npx -y mcp-server-security-scanner
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"vpatser1-mcp-server-security-scanner": {
"type": "local",
"command": [
"npx",
"-y",
"mcp-server-security-scanner"
],
"enabled": true
}
}
} openclaw mcp add vpatser1-mcp-server-security-scanner --command npx --arg -y --arg mcp-server-security-scanner
mcp_servers:
vpatser1-mcp-server-security-scanner:
command: "npx"
args: ["-y", "mcp-server-security-scanner"] {
"mcpServers": {
"vpatser1-mcp-server-security-scanner": {
"command": "npx",
"args": [
"-y",
"mcp-server-security-scanner"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 4 Aug 26 60
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 7 Aug 2026 · Analysed npm/[email protected]
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Dependencies 95 packages
| Packages resolved | 95 |
|---|---|
| Deprecated | 95 |
| Stale | 29 |
| Tree resolution | Partial |
The dependency tree was only partially resolved, so these counts may be incomplete.
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.
check_cves Check Known CVEs ~111
Checks a list of MCP server names and optional versions against a database of known CVEs in the MCP ecosystem (covering path traversal, SSRF, auth bypass, prompt injection, data exfiltration, command injection, and SQL injection). Returns matching CVEs with severity, CVSS scores, and remediation steps.
| Name | Type | Req | Description |
|---|---|---|---|
| listAll | boolean | – | If true, returns the full CVE database instead of checking specific servers |
| servers | array | yes | List of MCP servers to check for known CVEs |
No output schema declared.
No examples provided.
generate_report Generate Security Report ~140
Generates a comprehensive security report from scan results. Includes an executive summary with overall risk score (0-100), detailed findings with remediation steps, and a SOC 2 compliance checklist. Output is Markdown-formatted.
| Name | Type | Req | Description |
|---|---|---|---|
| authValidation | object | – | Results from validate_auth |
| configScan | object | – | Results from scan_config |
| cveCheck | object | – | Results from check_cves |
| findings | array | – | Direct array of findings to report on. Use this as a simple alternative to passing structured scan results. If provided alongside structured results, these findings are merged in. |
| toolScan | object | – | Results from scan_tool_definitions |
No output schema declared.
No examples provided.
scan_config Scan MCP Configuration ~85
Scans an MCP configuration file (claude_desktop_config.json, .mcp.json, etc.) for security vulnerabilities including hardcoded secrets, excessive permissions, insecure transports, missing authentication, and known vulnerable server versions.
| Name | Type | Req | Description |
|---|---|---|---|
| configPath | string | yes | Absolute or relative path to the MCP configuration file to scan (e.g. ~/.claude/claude_desktop_config.json) |
No output schema declared.
No examples provided.
scan_tool_definitions Scan Tool Definitions ~58
Analyzes MCP tool definitions for security vulnerabilities including prompt injection vectors, tool poisoning patterns, overly broad filesystem access, command injection risks, and data exfiltration patterns.
| Name | Type | Req | Description |
|---|---|---|---|
| tools | array | yes | Array of tool definition objects to scan |
No output schema declared.
No examples provided.
validate_auth Validate Authentication Configuration ~89
Validates OAuth 2.1, API key, or bearer token authentication configuration for an MCP server. Checks for proper PKCE usage, token storage security, redirect URI validation, token expiration settings, and overall auth best practices.
| Name | Type | Req | Description |
|---|---|---|---|
| authConfig | object | yes | Authentication configuration object to validate. OAuth fields can be nested under 'oauth' or provided at the top level in camelCase or snake_case. |
No output schema declared.
No examples provided.