Skip to main content
Glama
gemini2026

Documentation Search MCP Server

by gemini2026

snyk_scan_library

Scan libraries for security vulnerabilities using Snyk analysis. Identify risks, check licenses, and get remediation guidance for packages in ecosystems like npm, PyPI, or Maven.

Instructions

Scan a library using Snyk for comprehensive security analysis. Args: library_name: Name of the library to scan version: Version of the library (default: "latest") ecosystem: Package ecosystem ("pypi", "npm", "maven", etc.) Returns: Detailed security report from Snyk including vulnerabilities, licenses, and remediation advice

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
library_nameYes
versionNolatest
ecosystemNopypi

Implementation Reference

  • The primary handler function for the 'snyk_scan_library' MCP tool. Registers the tool via @mcp.tool(), handles input parameters, performs Snyk connection test and package scan, formats the security report with vulnerabilities, licenses, and recommendations.
    @mcp.tool() async def snyk_scan_library( library_name: str, version: str = "latest", ecosystem: str = "pypi" ): """ Scan a library using Snyk for comprehensive security analysis. Args: library_name: Name of the library to scan version: Version of the library (default: "latest") ecosystem: Package ecosystem ("pypi", "npm", "maven", etc.) Returns: Detailed security report from Snyk including vulnerabilities, licenses, and remediation advice """ from .snyk_integration import snyk_integration try: # Test connection first connection_test = await snyk_integration.test_connection() if connection_test["status"] != "connected": return { "error": "Snyk integration not configured", "details": connection_test.get("error", "Unknown error"), "setup_instructions": [ "1. Sign up for Snyk account at https://snyk.io", "2. Get API token from your Snyk account settings", "3. Set SNYK_API_KEY environment variable", "4. Optionally set SNYK_ORG_ID for organization-specific scans", ], } # Perform the scan package_info = await snyk_integration.scan_package( library_name, version, ecosystem ) return { "library": library_name, "version": version, "ecosystem": ecosystem, "scan_timestamp": datetime.now().isoformat(), "vulnerability_summary": { "total": len(package_info.vulnerabilities), "critical": package_info.severity_counts.get("critical", 0), "high": package_info.severity_counts.get("high", 0), "medium": package_info.severity_counts.get("medium", 0), "low": package_info.severity_counts.get("low", 0), }, "vulnerabilities": [ { "id": vuln.id, "title": vuln.title, "severity": vuln.severity.value, "cvss_score": vuln.cvss_score, "cve": vuln.cve, "is_patchable": vuln.is_patchable, "upgrade_path": vuln.upgrade_path[:3] if vuln.upgrade_path else [], "snyk_url": f"https://snyk.io/vuln/{vuln.id}", } for vuln in package_info.vulnerabilities[:10] # Limit to top 10 ], "license_info": [ { "name": license.name, "type": license.type, "spdx_id": license.spdx_id, "is_deprecated": license.is_deprecated, } for license in package_info.licenses ], "recommendations": [ "πŸ” Review all critical and high severity vulnerabilities", "πŸ“¦ Update to latest secure version if available", "βš–οΈ Ensure license compliance with your organization's policies", "πŸ”„ Set up continuous monitoring for this package", ], } except Exception as e: return { "error": f"Snyk scan failed: {str(e)}", "library": library_name, "version": version, }
  • Core helper method that executes the Snyk API scan for a specific package/version/ecosystem, handles caching, creates mock manifest payloads, parses responses, and returns structured SnykPackageInfo.
    async def scan_package( self, package_name: str, version: str, ecosystem: str = "pypi" ) -> SnykPackageInfo: """Scan a single package for vulnerabilities""" cache_key = f"package_{ecosystem}_{package_name}_{version}" if self._is_cached(cache_key): return self.cache[cache_key]["data"] ecosystem_map = { "pypi": "pip", "npm": "npm", "maven": "maven", "gradle": "gradle", "nuget": "nuget", } snyk_ecosystem = ecosystem_map.get(ecosystem.lower(), "pip") try: async with httpx.AsyncClient(timeout=self.timeout) as client: # Test endpoint for vulnerabilities test_payload = { "encoding": "plain", "files": { ( "requirements.txt" if snyk_ecosystem == "pip" else "package.json" ): { "contents": ( f"{package_name}=={version}" if snyk_ecosystem == "pip" else json.dumps( {"dependencies": {package_name: version}} ) ) } }, } response = await client.post( f"{self.base_url}/v1/test/{snyk_ecosystem}", headers=self._get_headers(), json=test_payload, ) if response.status_code == 200: data = response.json() package_info = self._parse_package_scan_result( data, package_name, version, ecosystem ) # Cache the result self._cache_result(cache_key, package_info) return package_info else: # Return empty result for failed scans return SnykPackageInfo( name=package_name, version=version, ecosystem=ecosystem, vulnerabilities=[], licenses=[], severity_counts={ "critical": 0, "high": 0, "medium": 0, "low": 0, }, dependency_paths=[], is_direct_dependency=True, ) except Exception as e: print(f"Snyk scan error for {package_name}: {e}", file=sys.stderr) return SnykPackageInfo( name=package_name, version=version, ecosystem=ecosystem, vulnerabilities=[], licenses=[], severity_counts={"critical": 0, "high": 0, "medium": 0, "low": 0}, dependency_paths=[], is_direct_dependency=True, )
  • Global singleton instance of SnykIntegration used by the tool handler.
    snyk_integration = SnykIntegration()
  • MCP tool registration decorator for snyk_scan_library.
    @mcp.tool()
  • Tool schema defined by function signature and docstring describing inputs (library_name, version, ecosystem) and output format.
    library_name: str, version: str = "latest", ecosystem: str = "pypi" ): """ Scan a library using Snyk for comprehensive security analysis. Args: library_name: Name of the library to scan version: Version of the library (default: "latest") ecosystem: Package ecosystem ("pypi", "npm", "maven", etc.) Returns: Detailed security report from Snyk including vulnerabilities, licenses, and remediation advice """

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/gemini2026/documentation-search-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server