Pentest Tools
This MCP server provides AI assistants with direct access to penetration testing tools including nmap, gobuster, nikto, nuclei, ffuf, dirsearch, hydra, john, and hashcat for comprehensive security assessments. Built by Vyom Jain using Node.js with the Model Context Protocol SDK, it executes security tools as child processes and parses their output into structured JSON results, supporting various scan types from quick port scans to full vulnerability assessments and password cracking operations. The implementation includes hardcoded wordlist paths, configurable scan parameters, timeout handling, and a comprehensive scan mode that combines multiple tools automatically, making it valuable for security professionals conducting penetration tests, vulnerability assessments, and building AI assistants that need programmatic access to security testing capabilities without manual tool execution.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- security
- Source
- PulseMCP
- Repository
- github.com/vyomjain6904/pentest-mcp-server
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Pentest Tools from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.