Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
BHE_PORTNoBloodhound API port8080
BHE_DOMAINNoBloodhound API domain/IP address127.0.0.1
BHE_TOKEN_IDYesBloodhound API token ID
BHE_TOKEN_KEYYesBloodhound API token key
PROJECT_DIRECTORYYesAbsolute path for your project directory to save findings in

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription
save_partial_findingB

save partial findings for later use (like open ports, used protocols, versions etc.) if finding data is too long or already exists in another file dont save it

get_project_directory_filesC

read existing files from the project directory to see what findings and data have been saved

read_filesD

read a file

check_SMB_signingC

used to check smb signgings of an ip address or some range of ip addresses with the needed options

run_nmap_scanC

run an nmap scan on an ip or ip range (use the right nmap flags based on the first response)

generate_pwd_wordlistC

generate some password wordlist based on initial input of word(s), let this be the last resort if no other wordlist worked

enumerate_domain_usersC

enumerate users on an active directory domain, you can provide username or password if you have some

bruteforce_rid_usersC

Bruteforce rid to enumerate users

password_sprayD

spray passwords on an account or several accounts

ASREPRoastC

Retrieve the Kerberos 5 AS-REP etype 23 hash of users without or with Kerberos pre-authentication required

KerberoastD

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, part of these TGS tickets is encrypted with keys derived from user passwords. As a consequence, their credentials could be cracked offline.

get_john_formatsC

check available john format before cracking a hash

john_the_ripperC

cracking hashes using john based on format and a wordlist

spider_smb_sharesC

enumerate smb shares having username and password credentials and dump them into ~/.nxc/modules/nxc_spider_plus/{ip}.json and you'll find the directory inside ~/.nxc/modules/nxc_spider_plus/{ip} that has the data so you could read that. read readable files after you check what files exists and pull valuable information like old versions , hard coded secrets , misconfigurations .. If you see items listed in the share but didn't get downloaded raise the max_size and download again.

dump_ntds_ditC

dump NTdS.dit which contains users and their hashes if we have some valid credentials

command_executionC

execute powershell commands if we have pwned the user, possible to use ntlm or password for authentication

dump_sam_hashesC

dump sam hashes if we have some redentials using the sec dump which is similar to secretdump,use ntlm hash or normal password

bloodhound_ingestC

use the netexec's bloodhound feature to extract the json data to be uploaded to bloodhound database

check_moduleC

Call this before before using a module to check available exploit modules for a certain netexec supported protocol {rdp,ldap,winrm,smb,ssh,nfs,ftp,wmi,mssql,vnc} and based on the description of the modules chose one to perform

check_optionsC

After selecting the right module call this to check what options that module presents

use_moduleC

Call this to use the module with the right options and make sure to satisfy the need of certain variables like credentials etc.If no credentials are needed for the module or no valid credentials are found leave the username and password default (empty). Options syntax is ["option1=value1","options2=value2",...]

test_bloodhound_connectionB

connect to bloodhoundapi and get version

upload_zip_to_bloodhoundB

Upload data zip to bloodhound to ingest and analyze (wait until it gets ingested before testing queries)

list_saved_quereisB

list already saved queries in bloodhound

run_blooodhound_queryB

Run a bloodhound cypher query of your choice (use this to collect information about the network and potentially identify attack vectors)

certipy_scanC

Call this to enumerating Active Directory Certificate Services (AD CS) vulnerabilities. username syntax is: username@domain

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription
get_custom_queries

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/YoussefSahnoun/PentestMCP'

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