Trusted — Risk Score 0/100
Last scan:1 day ago Rescan
0 /100
mcp-best-practices
Build production MCP servers with the TypeScript SDK. Covers spec 2025-11-25, SDK v1.28+/v2, transport selection, tool design, error handling, security, performance, known bugs with workarounds, MCP extensions, MCP Apps, authorization extensions, and the MCP Registry.
This is a pure Markdown documentation skill containing only reference guides for MCP best practices — no executable code, scripts, or binary dependencies. All pre-scan flags are educational examples within security documentation sections, not actual malicious behavior.
Skill Namemcp-best-practices
Duration27.6s
Enginepi
Safe to install
No action needed. This skill is safe to use.
ResourceDeclaredInferredStatusEvidence
Filesystem NONE NONE No Read/Write tool declarations; skill contains only Markdown files
Network NONE NONE No WebFetch or network tool declarations
Shell NONE NONE No Bash tool declarations; pre-scan 'rm -rf /' is a documented attack example in…
Environment NONE NONE No environment variable access
Skill Invoke NONE NONE No skill_invoke capability declared
Clipboard NONE NONE No clipboard access
Browser NONE NONE No browser tool declared
Database NONE NONE No database access
1 Critical 2 High 20 findings
💀
Critical Dangerous Command 危险 Shell 命令
rm -rf /
references/security-auth.md:155
📡
High IP Address 硬编码 IP 地址
169.254.169.254
references/security-auth.md:124
📡
High IP Address 硬编码 IP 地址
169.254.0.0
references/security-auth.md:128
🔗
Medium External URL 外部 URL
https://www.apache.org/licenses/
LICENSE.txt:3
🔗
Medium External URL 外部 URL
https://spec.modelcontextprotocol.io
SKILL.md:16
🔗
Medium External URL 外部 URL
https://modelcontextprotocol.io/registry/about
SKILL.md:22
🔗
Medium External URL 外部 URL
https://datatracker.ietf.org/doc/html/draft-ietf-oauth-v2-1-13
SKILL.md:309
🔗
Medium External URL 外部 URL
https://modelcontextprotocol.io/seps/2133-extensions
references/extensions-registry.md:70
🔗
Medium External URL 外部 URL
https://modelcontextprotocol.io/community/sep-guidelines
references/extensions-registry.md:72
🔗
Medium External URL 外部 URL
https://modelcontextprotocol.io/registry/quickstart
references/extensions-registry.md:171
🔗
Medium External URL 外部 URL
https://modelcontextprotocol.io/registry/github-actions
references/extensions-registry.md:173
🔗
Medium External URL 外部 URL
https://modelcontextprotocol.io/registry/versioning
references/extensions-registry.md:185
🔗
Medium External URL 外部 URL
https://mcpui.dev/
references/mcp-apps.md:43
🔗
Medium External URL 外部 URL
https://apps.extensions.modelcontextprotocol.io/api/documents/Patterns.html#configuring-csp-and-cors
references/mcp-apps.md:217
🔗
Medium External URL 外部 URL
https://apps.extensions.modelcontextprotocol.io/api/modules/app-bridge.html
references/mcp-apps.md:292
🔗
Medium External URL 外部 URL
https://apps.extensions.modelcontextprotocol.io/api/
references/mcp-apps.md:294
🔗
Medium External URL 外部 URL
https://evil.com/exfil
references/security-auth.md:154
🔗
Medium External URL 外部 URL
https://your-server.com/mcp
references/security-auth.md:210
🔗
Medium External URL 外部 URL
https://auth.your-server.com
references/security-auth.md:211
🔗
Medium External URL 外部 URL
https://mcp.example.com/.well-known/oauth-protected-resource
references/security-auth.md:236

File Tree

9 files · 95.0 KB · 2433 lines
Markdown 8f · 2271L Text 1f · 162L
├─ 📁 references
│ ├─ 📝 error-handling.md Markdown 263L · 9.0 KB
│ ├─ 📝 extensions-registry.md Markdown 233L · 9.6 KB
│ ├─ 📝 mcp-apps.md Markdown 294L · 9.5 KB
│ ├─ 📝 security-auth.md Markdown 251L · 11.2 KB
│ ├─ 📝 tool-schema-guide.md Markdown 289L · 9.4 KB
│ ├─ 📝 transport-patterns.md Markdown 233L · 8.5 KB
│ └─ 📝 v2-migration.md Markdown 332L · 9.8 KB
├─ 📄 LICENSE.txt Text 162L · 8.9 KB
└─ 📝 SKILL.md Markdown 376L · 19.0 KB

Security Positives

✓ No executable code or scripts present — pure documentation skill
✓ No dependencies (no package.json, requirements.txt, etc.)
✓ All pre-scan flags are false positives: 'rm -rf /' and AWS metadata IPs are educational examples in security-auth.md
✓ SKILL.md accurately describes the skill as a decision reference for MCP best practices
✓ No credential harvesting, data exfiltration, obfuscation, or persistence mechanisms
✓ No supply chain risks — no third-party dependencies