// SCAN REPORT

pentestMCP

36 tools. 21 can modify or destroy data without limits.

21 write tools that can modify data. Rate limits recommended.

Last updated: 11 Jun 2026

21 can modify or destroy data

15 read-only

36 tools total

Community server · catalogue entry verified 11/06/2026

How to control pentestMCP ↓

TOOL MAP

Read (15) Write / Execute (21) Destructive / Financial (0)

MOST DANGEROUS TOOLS

High Risk

Execute · High launch_arjun_scan This tool executes an active security scanner against external targets. Execute · High launch_gofang_scan Launching a scan (Gofang, a fuzzing/scanning tool) executes code against external systems whose behavior and impact depend on the agent's choice of targets and configuration. Execute · High launch_nmap_scan This is Execute rather than Read because Nmap scans trigger active network operations and observable side effects beyond passive data retrieval. Execute · High launch_nuclei_scan Nuclei is a vulnerability scanner that executes probes and payloads against target systems.

21 of pentestMCP's 36 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

HOW TO CONTROL PENTESTMCP

PolicyLayer is an MCP gateway — it sits between your AI agents and pentestMCP, and nothing reaches the server without passing your rules. These are the rules we recommend:

Cap read operations

{
  "ad_dcsync": {
    "limits": [
      {
        "counter": "ad_dcsync_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register pentestMCP — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON PENTESTMCP →

Free to start. No card required.

ALL 36 PENTESTMCP TOOLS

EXECUTE 21 tools

Execute launch_arjun_scan Launch Arjun (HTTP parameter discovery tool) to find hidden HTTP parameters. Execute launch_gofang_scan launch_gofang_scan Execute launch_nmap_scan Launch a Nmap scan against the given target with optional arguments. Execute launch_nuclei_scan Launch a Nuclei scan against the given target with optional arguments. Execute run_curl_tool Run a curl command against the given target with the provided options. Execute run_dig_tool Run a dig command against the given domain with the provided options. Execute run_gobuster_scan run_gobuster_scan Execute run_harvester run_harvester Execute run_searchsploit Run Searchsploit against the given query with optional arguments. Execute run_sqlmap_tool Run a SQLMap scan against the given target with the provided options. Execute run_subfinder Run Subfinder against the given URL with the provided arguments. Execute ad_asreproast AS-REP Roasting attack to harvest Kerberos hashes Execute ad_bloodhound_collect ad_bloodhound_collect Execute ad_certipy_enum ad_certipy_enum Execute ad_check_credentials Quick credential validation Execute ad_coerce_petitpotam ad_coerce_petitpotam Execute ad_coerce_printerbug ad_coerce_printerbug Execute ad_kerberoast ad_kerberoast Execute ad_password_spray ad_password_spray Execute ad_responder_poison ad_responder_poison Execute ad_relay_setup ad_relay_setup

READ 15 tools

Read ad_dcsync ad_dcsync Read ad_ldap_dump Comprehensive LDAP dump Read ad_secrets_dump ad_secrets_dump Read ad_shares_enum Enumerate SMB shares and permissions Read ad_smb_signing_check Check SMB signing status to identify relay targets Read ad_user_enum Enumerate domain users using NetExec Read check_gobuster_status Check the status of a Gobuster scan. Read check_harvester_output One-shot check: has theHarvester produced its JSON results yet? Read check_sqlmap_status Non-blocking status check for SQLMap scan: Read fetch_arjun_results Fetch results from a previously launched Arjun scan. Read fetch_file Fetch the contents of any file. Useful for reading full logs, output files, or resources. Read fetch_gofang_results fetch_gofang_results Read fetch_nmap_results Non-blocking fetch for Nmap scan results: Read fetch_nuclei_results Non-blocking fetch for Nuclei scan results: Read fetch_whois_data Fetch WHOIS data for the given domain.

RELATED SERVERS

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Is the pentest MCP server safe to use without restrictions? +

The pentestMCP server is primarily read-only with 15 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the pentest MCP server expose? +

36 tools across 3 categories: Execute, Read, Write. 15 are read-only. 21 can modify, create, or delete data.

How do I enforce a policy on pentestMCP? +

Register the pentest MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every pentestMCP tool call.

Deterministic rules across all 36 pentestMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON PENTESTMCP →

Free to start. No card required.

36 pentestMCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

pentestMCP

// TOOL MAP

// MOST DANGEROUS TOOLS

// HOW TO CONTROL PENTESTMCP

// ALL 36 PENTESTMCP TOOLS

// RELATED SERVERS

// FAQ