// SCAN REPORT

PentestMCP

26 tools. 7 can modify or destroy data without limits.

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

Last updated: 28 Jun 2026

7 can modify or destroy data

19 read-only

26 tools total

Community server · catalogue entry verified 28/06/2026

How to control PentestMCP ↓

TOOL MAP

What PentestMCP exposes to your agents

Read (19) Write / Execute (7) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous PentestMCP tools

Execute · Medium command_execution execute powershell commands if we have pwned the user, possible to use ntlm or password for authentication Execute · Medium Kerberoast The goal of Kerberoasting is to harvest TGS tickets for services that run on behalf of user accounts in the AD, not computer accounts. Thus, Execute · Medium run_blooodhound_query Run a bloodhound cypher query of your choice (use this to collect information about the network and potentially identify attack vectors) Execute · Medium run_nmap_scan run an nmap scan on an ip or ip range (use the right nmap flags based on the first response)

7 of PentestMCP's 26 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

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:

Rate limit write operations

{
  "generate_pwd_wordlist": {
    "limits": [
      {
        "counter": "generate_pwd_wordlist_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "ASREPRoast": {
    "limits": [
      {
        "counter": "asreproast_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 →

Instant setup, no code required.

FULL CATALOGUE

All 26 PentestMCP tools

EXECUTE 4 tools

Execute command_execution execute powershell commands if we have pwned the user, possible to use ntlm or password for authentication Execute Kerberoast The goal of Kerberoasting is to harvest TGS tickets for services that run on behalf of user accounts in the AD Execute run_blooodhound_query Run a bloodhound cypher query of your choice (use this to collect information about the network and potentiall Execute run_nmap_scan run an nmap scan on an ip or ip range (use the right nmap flags based on the first response)

WRITE 3 tools

Write generate_pwd_wordlist generate some password wordlist based on initial input of word(s), let this be the last resort if no other wor Write save_partial_finding save partial findings for later use (like open ports, used protocols, versions etc.) if finding data is too lo Write upload_zip_to_bloodhound Upload data zip to bloodhound to ingest and analyze (wait until it gets ingested before testing queries)

READ 19 tools

Read ASREPRoast Retrieve the Kerberos 5 AS-REP etype 23 hash of users without or with Kerberos pre-authentication required Read bloodhound_ingest use the netexec Read bruteforce_rid_users Bruteforce rid to enumerate users Read certipy_scan Call this to enumerating Active Directory Certificate Services (AD CS) vulnerabilities. username syntax is: us Read check_module Call this before before using a module to check available exploit modules for a certain netexec supported prot Read check_options After selecting the right module call this to check what options that module presents Read check_SMB_signing used to check smb signgings of an ip address or some range of ip addresses with the needed options Read dump_ntds_dit dump NTdS.dit which contains users and their hashes if we have some valid credentials Read dump_sam_hashes dump sam hashes if we have some redentials using the sec dump which is similar to secretdump,use ntlm hash or Read enumerate_domain_users enumerate users on an active directory domain, you can provide username or password if you have some Read get_john_formats check available john format before cracking a hash Read get_project_directory_files read existing files from the project directory to see what findings and data have been saved Read john_the_ripper cracking hashes using john based on format and a wordlist Read list_saved_quereis list already saved queries in bloodhound Read password_spray spray passwords on an account or several accounts Read read_files read a file Read spider_smb_shares enumerate smb shares having username and password credentials and dump them into ~/.nxc/modules/nxc_spider_plu Read test_bloodhound_connection connect to bloodhoundapi and get version Read use_module Call this to use the module with the right options and make sure to satisfy the need of certain variables like

EXPLORE

Related servers

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

FAQ

Questions about PentestMCP

How do I prevent bulk modifications through PentestMCP? +

The PentestMCP server has 3 write tools including generate_pwd_wordlist, save_partial_finding, upload_zip_to_bloodhound. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach PentestMCP.

How many tools does the Pentest MCP server expose? +

26 tools across 3 categories: Execute, Read, Write. 19 are read-only. 7 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 26 PentestMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON PENTESTMCP →

Instant setup, no code required.

26 PentestMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.