Blog
/
Network
/
June 23, 2023

How Darktrace Quickly Foiled An Information Stealer

Discover how Darktrace thwarted the CryptBot malware in just 2 seconds. Learn about this fast-moving threat and the defense strategies employed.
Inside the SOC
Darktrace cyber analysts are world-class experts in threat intelligence, threat hunting and incident response, and provide 24/7 SOC support to thousands of Darktrace customers around the globe. Inside the SOC is exclusively authored by these experts, providing analysis of cyber incidents and threat trends, based on real-world experience in the field.
Written by
Alexandra Sentenac
Cyber Analyst
Default blog image
23
Jun 2023

The recent trend of threat actors using information stealer malware, designed to gather and exfiltrate confidential data, shows no sign of slowing. With new or updated info-stealer strains appearing in the wild on a regular basis, it came as no surprise to see a surge in yet another prolific variant in late 2022, CryptBot.

What is CryptBot?

CryptBot is a Windows-based trojan malware that was first discovered in the wild in December 2019. It belongs to the prolific category of information stealers whose primary objective, as the name suggests, is to gather information from infected devices and send it to the threat actor.

ZeuS was reportedly the first info-stealer to be discovered, back in 2006. After its code was leaked, many other variants came to light and have been gaining popularity amongst cyber criminals [1] [2] [3]. Indeed, Inside the SOC has discussed multiple infections across its customer base associated with several types of stealers in the past months [4] [5] [6] [7]. 

The Darktrace Threat Research team investigated CryptBot infections on the digital environments of more than 40 different Darktrace customers between October 2022 and January 2023. Darktrace DETECT™ and its anomaly-based approach to threat detection allowed it to successfully identify the unusual activity surrounding these info-stealer infections on customer networks. Meanwhile, Darktrace RESPOND™, when enabled in autonomous response mode, was able to quickly intervene and prevent the exfiltration of sensitive company data.

Why is info-stealer malware popular?

It comes as no surprise that info-stealers have “become one of the most discussed malware types on the cybercriminal underground in 2022”, according to Accenture’s Cyber Threat Intelligence team [10]. This is likely in part due to the fact that:

More sensitive data on devices

Due to the digitization of many aspects of our lives, such as banking and social interactions, a trend accelerated by the COVID-19 pandemic.

Cost effective

Info-stealers provide a great return on investment (ROI) for threat actors looking to exfiltrate data without having to do the traditional internal reconnaissance and data transfer associated with data theft. Info-stealers are usually cheap to purchase and are available through Malware-as-a-Service (MaaS) offerings, allowing less technical and resourceful threat actors in on the stealing action. This makes them a prevalent threat in the malware landscape. 

How does CryptBot work?

The techniques employed by info-stealers to gather and exfiltrate data as well as the type of data targeted vary from malware to malware, but the data targeted typically includes login credentials for a variety of applications, financial information, cookies and global information about the infected computer [8]. Given its variety and sensitivity, threat actors can leverage the stolen data in several ways to make a profit. In the case of CryptBot, the data obtained is sold on forums or underground data marketplaces and can be later employed in higher profile attacks [9]. For example, stolen login information has previously been leveraged in credential-based attacks, which can successfully bypass authentication-based security measures, including multi-factor authentication (MFA). 

CryptBot functionalities

Like many information stealers, CryptBot is designed to steal a variety of sensitive personal and financial information such as browser credentials, cookies and history information and social media accounts login information, as well as cryptocurrency wallets and stored credit card information [11]. General information (e.g., OS, installed applications) about the infected computer is also retrieved. Browsers targeted by CryptBot include Chrome, Firefox, and Edge. In early 2022, CryptBot’s code was revamped in order to streamline its data extraction capabilities and improve its overall efficiency, an update that coincided with a rise in the number of infections [11] [12].

Some of CryptBot's functionalities were removed and its exfiltration process was streamlined, which resulted in a leaner payload, around half its original size and a quicker infection process [11]. Some of the features removed included sandbox detection and evasion functionalities, the collection of desktop text files and screen captures, which were deemed unnecessary. At the same time, the code was improved in order to include new Chrome versions released after CryptBot’s first appearance in 2019. Finally, its exfiltration process was simplified: prior to its 2022 update, the malware saved stolen data in two separate folders before sending it to two separate command and control (C2) domains. Post update, the data is only saved in one location and sent to one C2 domain, which is hardcoded in the C2 transmission function of the code. This makes the infection process much more streamlined, taking only a few minutes from start to finish. 

Aside from the update to its malware code, CryptBot regularly updates and refreshes its C2 domains and dropper websites, making it a highly fluctuating malware with constantly new indicators of compromise and distribution sites. 

Even though CryptBot is less known than other info-stealers, it was reportedly infecting thousands of devices daily in the first months of 2020 [13] and its continued prevalence resulted in Google taking legal action against its distribution infrastructure at the end of April 2023 [14].  

How is CryptBot obtained?

CryptBot is primarily distributed through malicious websites offering free and illegally modified software (i.e., cracked software) for common commercial programs (e.g., Microsoft Windows and Office, Adobe Photoshop, Google Chrome, Nitro PDF Pro) and video games. From these ‘malvertising’ pages, the user is redirected through multiple sites to the actual payload dropper page [15]. This distribution method has seen a gain in popularity amongst info-stealers in recent months and is also used by other malware families such as Raccoon Stealer and Vidar [16] [17].

A same network of cracked software websites can be used to download different malware strains, which can result in multiple simultaneous infections. Additionally, these networks often use search engine optimization (SEO) in order to make adverts for their malware distributing sites appear at the top of the Google search results page, thus increasing the chances of the malicious payloads being downloaded.

Furthermore, CryptBot leverages Pay-Per-Install (PPI) services such as 360Installer and PrivateLoader, a downloader malware family used to deliver payloads of multiple malware families operated by different threat actors [18] [19] [20]. The use of this distribution method for CryptBot payloads appears to have stemmed from its 2022 update. According to Google, 161 active domains were associated with 360Installer, of which 90 were associated with malware delivery activities and 29 with the delivery of CryptBot malware specifically. Google further identified hundreds of domains used by CryptBot as C2 sites, all of which appear to be hosted on the .top top-level domain [21].

This simple yet effective distribution tactic, combined with the MaaS model and the lucrative prospects of selling the stolen data resulted in numerous infections. Indeed, CryptBot was estimated to have infected over 670,000 computers in 2022 [14]. Even though the distribution method chosen means that most of the infected devices are likely to be personal computers, bring your own device (BYOD) policies and users’ tendency to reuse passwords means that corporate environments are also at risk. 

CryptBot Attack Overview

In some cases observed by Darktrace, after connecting to malvertising websites, devices were seen making encrypted SSL connections to file hosting services such as MediaFire or Mega, while in others devices were observed connecting to an endpoint associated with a content delivery network. This is likely the location from where the malware payload was downloaded alongside cracked software, which is executed by the unsuspecting user. As the user expects to run an executable file to install their desired software, the malware installation often happens without the user noticing.

Some of the malvertising sites observed by Darktrace on customer deployments were crackful[.]com, modcrack[.]net, windows-7-activator[.]com and office-activator[.]com. However, in many cases detected by Darktrace, CryptBot was propagated via websites offering trojanized KMSPico software (e.g., official-kmspico[.]com, kmspicoofficial[.]com). KMSPico is a popular Microsoft Windows and Office product activator that emulates a Windows Key Management Services (KMS) server to activate licenses fraudulently. 

Once it has been downloaded and executed, CryptBot will search the system for confidential information and create a folder with a seemingly randomly generated name, matching the regex [a-zA-Z]{10}, to store the gathered sensitive data, ready for exfiltration. 

Figure 1: Packet capture (PCAP) of an HTTP POST request showing the file with the stolen data being sent over the connection.
Figure 1: Packet capture (PCAP) of an HTTP POST request showing the file with the stolen data being sent over the connection.

This data is then sent to the C2 domain via HTTP POST requests on port 80 to the URI /gate.php. As previously stated, CryptBot C2 infrastructure is changed frequently and many of the domains seen by Darktrace had been registered within the previous 30 days. The domain names detected appeared to have been generated by an algorithm, following the regex patterns [a-z]{6}[0-9]{2,3}.top or [a-z]{6}[0-9]{2,3}.cfd. In several cases, the C2 domain had not been flagged as malicious by other security vendors or had just one detection. This is likely because of the frequent changes in the C2 infrastructure operated by the threat actors behind CryptBot, with new malicious domains being created periodically to avoid detection. This makes signature-based security solutions much less efficient to detect and block connections to malicious domains. Additionally, the fact that the stolen data is sent over regular HTTP POST requests, which are used daily as part of a multitude of legitimate processes such as file uploads or web form submissions, allows the exfiltration connections to blend in with normal and legitimate traffic making it difficult to isolate and detect as malicious activity. 

In this context, anomaly-based security detections such as Darktrace DETECT are the best way to pick out these anomalous connections amidst legitimate Internet traffic. In the case of CryptBot, two DETECT models were seen consistently breaching for CryptBot-related activity: ‘Device / Suspicious Domain’, breaching for connections to 100% rare C2 .top domains, and ‘Anomalous Connection / POST to PHP on New External Host’, breaching on the data exfiltration HTTP POST request. 

In deployments where Darktrace RESPOND was deployed, a RESPOND model breached within two seconds of the first HTTP POST request. If enabled in autonomous mode, RESPOND would block the data exfiltration connections, thus preventing the data safe from being sold in underground forums to other threat actors. In one of the cases investigated by Darktrace’s Threat Research team, DETECT was able to successfully identify and alert the customer about CryptBot-related malicious activity on a device that Darktrace had only begun to monitor one day before, showcasing how fast Darktrace’s Self-Learning AI learns every nuance of customer networks and the devices within it.

In most cases investigated by Darktrace, fewer than 5 minutes elapsed between the first connection to the endpoint offering free cracked software and the data being exfiltrated to the C2 domain. For example, in one of the attack chains observed in a university’s network, a device was seen connecting to the 100% rare endpoint official-kmspico[.]com at 16:53:47 (UTC).

Device Event Log showing SSL connections to the official-kmspico[.]com malvertising website.
Figure 2: Device Event Log showing SSL connections to the official-kmspico[.]com malvertising website.

One minute later, at 16:54:19 (UTC), the same device was seen connecting to two mega[.]co[.]nz subdomains and downloading around 13 MB of data from them. As mentioned previously, these connections likely represent the CryptBot payload and cracked software download.

Device Event Log showing SSL connections to mega[.]com endpoints following the connection to the malvertising site.
Figure 3: Device Event Log showing SSL connections to mega[.]com endpoints following the connection to the malvertising site.

At 16:56:01 (UTC), Darktrace detected the device making a first HTTP POST request to the 100% rare endpoint, avomyj24[.]top, which has been associated with CryptBot’s C2 infrastructure [22]. This initial HTTP POST connection likely represents the transfer of confidential data to the attacker’s infrastructure.

Device Event Log showing HTTP connections made by the infected device to the C2 domain. 
Figure 4: Device Event Log showing HTTP connections made by the infected device to the C2 domain. 

The full attack chain, from visiting the malvertising website to the malicious data egress, took less than three minutes to complete. In this circumstance, the machine-speed detection and response capabilities offered by Darktrace DETECT and RESPOND are paramount in order to stop CryptBot before it can successfully exfiltrates sensitive data. This is an incredibly quick infection timeline, with no lateral movement nor privilege escalation required to carry out the malware’s objective. 

Device Event Log showing the DETECT and RESPOND models breached during the attack. 
Figure 5: Device Event Log showing the DETECT and RESPOND models breached during the attack. 

Darktrace Cyber AI Analyst incidents were also generated as a result of this activity, displaying all relevant information in one panel for easy review by customer security teams.

Cyber AI Analyst event log showing the HTTP connections made by the breach device to the C2 endpoint.
Figure 6: Cyber AI Analyst event log showing the HTTP connections made by the breach device to the C2 endpoint.

Conclusion 

CryptBot info-stealer is fast, efficient, and apt at evading detection given its small size and swift process of data gathering and exfiltration via legitimate channels. Its constantly changing C2 infrastructure further makes it difficult for traditional security tools that really on rules and signatures or known indicators of compromise (IoCs) to detect these infections. 

In the face of such a threat, Darktrace’s anomaly-based detection allows it to recognize subtle deviations in a device’s pattern of behavior that may signal an evolving threat and instantly bring it to the attention of security teams. Darktrace DETECT is able to distinguish between benign activity and malicious behavior, even from newly monitored devices, while Darktrace RESPOND can move at machine-speed to prevent even the fastest moving threat actors from stealing confidential company data, as it demonstrated here by stopping CryptBot infections in as little as 2 seconds.

Credit to Alexandra Sentenac, Cyber Analyst, Roberto Romeu, Senior SOC Analyst

Darktrace Model Detections  

AI Analyst Coverage 

  • Possible HTTP Command and Control  

DETECT Model Breaches  

  • Device / Suspicious Domain 
  • Anomalous Connection / POST to PHP on New External Host 
  • Anomalous Connection / Multiple HTTP POSTs to Rare Hostname 
  • Compromise / Multiple SSL to Rare DGA Domains

List of IOCs

Indicator Type Description
luaigz34[.]top Hostname CryptBot C2 endpoint
watibt04[.]top Hostname CryptBot C2 endpoint
avolsq14[.]top Hostname CryptBot C2 endpoint

MITRE ATT&CK Mapping

Category Technique Tactic
INITIAL ACCESS Drive-by Compromise - T1189 N/A
COMMAND AND CONTROL Web Protocols - T1071.001 N/A
COMMAND AND CONTROL Domain Generation Algorithm - T1568.002 N/A

References

[1] https://www.malwarebytes.com/blog/threats/info-stealers

[2] https://cybelangel.com/what-are-infostealers/

[3] https://ke-la.com/information-stealers-a-new-landscape/

[4] https://darktrace.com/blog/vidar-info-stealer-malware-distributed-via-malvertising-on-google

[5] https://darktrace.com/blog/a-surge-of-vidar-network-based-details-of-a-prolific-info-stealer 

[6] https://darktrace.com/blog/laplas-clipper-defending-against-crypto-currency-thieves-with-detect-respond

[7] https://darktrace.com/blog/amadey-info-stealer-exploiting-n-day-vulnerabilities 

[8] https://cybelangel.com/what-are-infostealers/

[9] https://webz.io/dwp/the-top-10-dark-web-marketplaces-in-2022/

[10] https://www.accenture.com/us-en/blogs/security/information-stealer-malware-on-dark-web

[11] https://www.bleepingcomputer.com/news/security/revamped-cryptbot-malware-spread-by-pirated-software-sites/

[12] https://blogs.blackberry.com/en/2022/03/threat-thursday-cryptbot-infostealer

[13] https://www.deepinstinct.com/blog/cryptbot-how-free-becomes-a-high-price-to-pay

[14] https://blog.google/technology/safety-security/continuing-our-work-to-hold-cybercriminal-ecosystems-accountable/

[15] https://asec.ahnlab.com/en/31802/

[16] https://darktrace.com/blog/the-last-of-its-kind-analysis-of-a-raccoon-stealer-v1-infection-part-1

[17] https://www.trendmicro.com/pt_br/research/21/c/websites-hosting-cracks-spread-malware-adware.html

[18] https://intel471.com/blog/privateloader-malware

[19] https://cyware.com/news/watch-out-pay-per-install-privateloader-malware-distribution-service-is-flourishing-888273be 

[20] https://regmedia.co.uk/2023/04/28/handout_google_cryptbot_complaint.pdf

[21] https://www.bankinfosecurity.com/google-wins-court-order-to-block-cryptbot-infrastructure-a-21905

[22] https://github.com/stamparm/maltrail/blob/master/trails/static/malware/cryptbot.txt

Inside the SOC
Darktrace cyber analysts are world-class experts in threat intelligence, threat hunting and incident response, and provide 24/7 SOC support to thousands of Darktrace customers around the globe. Inside the SOC is exclusively authored by these experts, providing analysis of cyber incidents and threat trends, based on real-world experience in the field.
Written by
Alexandra Sentenac
Cyber Analyst

More in this series

No items found.

Blog

/

AI

/

November 17, 2026

How Microsoft and Darktrace Secure the AI-Powered Enterprise

Default blog imageDefault blog image

When legitimate activity creates business risk

AI is making information more accessible and enabling autonomous agents to act across enterprise systems. But legitimate access can still result in sensitive-data exposure, unintended actions, or activity that deviates from business expectations.

Microsoft's evolving security strategy recognizes this shift, emphasizing continuous risk assessment, stronger identity protection, and security that adapts as AI systems operate. For enterprises, the challenge is increasingly about recognizing when trusted activity introduces risk, even when existing controls are functioning as intended.

Where global intelligence meets deep business context

Microsoft brings global threat intelligence and comprehensive security capabilities, helping organizations protect identities, data, applications, and infrastructure. Its integrated approach connects security signals, governance, detection, and response across increasingly complex environments.

Darktrace complements these strengths with deep, organization-specific behavioral understanding. Powered by Adaptive AI, Darktrace continuously learns the patterns and relationships unique to each business, developing a Unique Behavioral Profile for each organization that helps distinguish meaningful threats from legitimate activity. By connecting identity, activity, context, and intent, it adds another dimension to security intelligence.

Together, Microsoft and Darktrace combine global intelligence with deeper knowledge of how each customer operates. Through supported integrations, this behavioral context enriches existing Microsoft security workflows, enabling more informed investigations and precise response.

This complementary approach extends across three interconnected areas of enterprise security- AI, People and Infrastructure. From understanding how AI and agents operate to protecting trusted communications and the infrastructure businesses depend on, Darktrace strengthens Microsoft's security capabilities with behavioral insight specific to each organization.

Understanding AI beyond permissions and policies

As AI moves into business-critical operations, security teams need to understand more than which applications and agents are approved. They need visibility into how AI is used, what information it accesses, and whether its actions remain aligned with business intent.

Microsoft provides extensive AI development, governance, and security capabilities. Darktrace / SECURE AI complements these with behavioral analysis across Shadow AI, prompts, agent identities and actions, and development risk. Policy Manager helps evaluate activity against organizational AI policies, while the announced integration with Microsoft Agent 365 is designed to enrich agent risk assessments with organization-specific behavioral signals. Together, these capabilities help organizations scale AI adoption with greater confidence.

Recognizing risk within trusted relationships

Sophisticated threats increasingly exploit established business relationships, familiar communications, and legitimate accounts. A message from a trusted supplier or an action taken through an authorized identity may appear routine until considered against the organization's normal behavior.

Darktrace / EMAIL complements Microsoft's native email, identity, and data protection capabilities by understanding how people and organizations communicate. This enables more precise detection of targeted phishing, business email compromise, account takeover, and data loss, supported by proportionate response. Integrations such as Unified Quarantine within Microsoft Defender for Office 365 bring this additional protection into existing security workflows.

Seeing the bigger picture behind an attack across domains

Threats rarely unfold within a single security domain. Suspicious identity activity, unexpected cloud connections, and unusual network behavior may appear unrelated until the relationships between them reveal a developing attack.

Darktrace / HYBRID NETWORK complements Microsoft's security capabilities with organization-specific behavioral detection across network, cloud, identity, and operational technology. Real-Time AI Analyst, including Cyber AI Analyst, connects related activity into investigated incidents that can be delivered into Microsoft Sentinel, helping security teams accelerate investigations and support targeted containment across the hybrid enterprise.

Turning security intelligence into business confidence

As AI becomes more deeply integrated into business operations, organizations need security that understands not only what technology can access, but how it behaves within their unique environment.

Microsoft and Darktrace bring complementary strengths to that challenge. By connecting global threat intelligence and integrated security capabilities with deep behavioral understanding, the partnership helps organizations recognize emerging risks, respond with greater precision, and strengthen their existing security investments.

The opportunity is to turn security intelligence into meaningful business context, enabling organizations to innovate and operate AI with confidence.

Darktrace named a 2026 Microsoft Partner of the Year Finalist for ISV Innovation

Darktrace has been named a finalist for the 2026 Microsoft Partner of the Year Award in the ISV Innovation category.  

This recognition reflects our collaboration with Microsoft to bring business context to enterprise security. By connecting Microsoft's global threat intelligence and integrated security capabilities with Darktrace's deep behavioral understanding, we help organizations recognize emerging risks and respond with greater precision across AI, People and Infrastructure.

Thank you to Microsoft, our customers, and our teams for their continued collaboration.

Meet Darktrace at Microsoft Ignite and the Microsoft Frontier Tour

Explore how Darktrace and Microsoft are bringing behavioral security to AI, people, and infrastructure.

Join Darktrace at Microsoft Ignite in San Francisco, November 17–19, or connect with our experts as we join the Microsoft Frontier Tour across 21 cities worldwide.

Meet Darktrace at Microsoft Ignite

Connect with Darktrace at the Microsoft Frontier Tour

[related-resource]

Continue reading
About the author

Blog

/

AI

/

November 13, 2026

Introducing Darktrace MCP: Connect your AI assistants to the Darktrace Behavioral Defense Platform

Default blog imageDefault blog image

The Darktrace MCP Server is now generally available to users of the Darktrace Platform Portal. It enables compatible AI assistants to query security data, retrieve Cyber AI Analyst findings, and execute supported actions across actively licensed Darktrace products. Customers can now use these capabilities in their own AI workflows to gather incident context, search telemetry, enrich investigations with information from other services, and carry out triage tasks.

What is MCP?
MCP is an open standard developed by Anthropic that lets AI systems connect to and use enterprise tools and data. Adoption of MCP servers creates an opportunity for SOC teams to move beyond isolated AI experiences toward truly operational AI workflows.

Available capabilities

The server exposes tools for three areas of security work:

  • Incident discovery and threat hunting. Retrieve model alerts and incident groups, search for relevant devices and investigate indicators of compromise. Assistants with access to other services can combine these results with external threat intelligence.
  • Investigation and analysis. Retrieve Cyber AI Analyst incident findings, examine related event data, and enrich the investigation with information from other platforms or external documentation.
  • Triage and workflow actions. Add comments, tags and statuses to alerts and assets, modify supported settings such as trusted domains and subnet details, or trigger a Cyber AI Analyst investigation.

Available capabilities depend on the licensed products connected to the server. The toolset also includes access to Secure AI prompt and shadow AI information, cloud misconfigurations and external exposure information, and Email threat trends and supported management functions.

The following examples show how the server’s discovery, investigation, and action capabilities can be combined within an AI assistant.

Check external threat indicators against your environment

An assistant can use Darktrace MCP alongside external threat intelligence to check whether reported indicators appear in an environment. Darktrace’s tools provide device information and endpoint context; the assistant’s other tools or connected services supply the external intelligence.

In this example, the assistant searched for recent threat reports, selected indicators of compromise (IoCs) to investigate, and checked for devices that had communicated with the reported IP addresses. It then examined endpoint information to put the matches into context.

Relevant Darktrace tools: search_devices, get_endpoint_information, get_model_alerts, get_incident_events

Example prompt: “See what IoCs are appearing in recent threat reports online, identify the most critical one from the last week, and then analyze to see if it exists in my environment.”

AI assistant output using external threat intelligence alongside data retrieved through the Darktrace MCP Server.

Enrich a Cyber AI Analyst investigation

Cyber AI Analyst provides Darktrace’s incident analysis. Through MCP, an assistant can retrieve those findings, explain specific parts of an incident, and bring in related data from other services.

In this example, the assistant examined a Potential AWS Account Hijack investigated by Cyber AI Analyst. It assembled a step-by-step account and raw event timeline, then consulted AWS documentation to add relevant prevention guidance. The assistant brings together the existing Darktrace analysis, supporting events, and external guidance in one response.

Relevant Darktrace tools: get_incident_groups, get_incident_events, get_detailed_events, get_ai_analyst_investigations, advanced_search

Example prompt: “Drill down on the identified potential AWS account hijack. Show me a detailed step-by-step of what happened using data from Cyber AI Analyst, including a raw event timeline, and provide info on how to prevent this from happening again using info from AWS documentation.”

AI assistant output combining Cyber AI Analyst findings and event data with guidance from AWS documentation. Some sensitive content has been redacted.

Work through triage with analyst confirmation

The server’s action tools allow an assistant to support repetitive triage tasks as well as retrieve information. For example, to improve efficiency of a daily triage workflow, an analyst could ask an AI assistant to present untriaged alerts one at a time, summarizing each issue and suggesting a next step for confirmation.

The example below shows the assistant proposing actions such as recording a finding, acknowledging an incident, tagging an asset, or triggering a Cyber AI Analyst investigation for more detail. The analyst chooses how to proceed.

Relevant Darktrace tools: get_model_alerts, update_model_alert, update_incident_group, manage_tags, create_ai_analyst_investigation

Example prompt: “Using the Darktrace MCP server, obtain all un-triaged alerts from the last 3 days and display them one at a time. Provide a summary of the issue, and a suggested triage and immediate response action. I will confirm what action should be performed.”

AI assistant output proposing triage actions using information retrieved through Darktrace MCP and asking the analyst how to proceed. Some sensitive content has been redacted.

Permissions and security considerations

The MCP server provides access to supported capabilities within the products a customer is licensed to use. Connections should follow the principle of least privilege, with access appropriate to the intended workflow.

A read-only connection mode is also available for workflows that do not require changes. This mode hides tools that mutate data; configuration details are provided in the Product Guide.

Some tools can change data or perform actions, including adding or removing asset tags, triggering Cyber AI Analyst investigations, and acting on assets. Consider which capabilities an assistant should be able to use before connecting it and retain human oversight of actions that could cause disruption or unwanted changes.

For further guidance, see:

Seven MCP risks CISOs should consider and how to prepare

Anthropic’s MCP Security Best Practices

Use the interface that suits the task

MCP gives customers another way to work with Darktrace alongside its product interfaces. Users may find that complex investigations requiring visual analysis, or strategic decisions involving impactful actions, are better suited to the graphical interfaces within Darktrace products. They can choose the approach that fits their workflow.

How to start using the Darktrace MCP Server

The Darktrace MCP Server is used to connect a compatible AI assistant to supported tools within your Darktrace deployment. The assistant can retrieve alerts and device information, draw on Cyber AI Analyst findings, and perform permitted actions across your licensed products.

To get started, you will need access to the Darktrace Platform Portal and a compatible AI assistant. Follow the Platform Portal MCP Server guide to find out how to create the required credentials and configure the connection today.

Contact a Darktrace representative to explore how the Darktrace MCP Server can support your security operations.

To learn more about Darktrace can help protect your MCP servers within your broader AI and agent use, discover Darktrace / SECURE AI.

‍

Appendix: Darktrace MCP available tools

The following tool catalogue reflects the list supplied for this announcement. Available tools depend on the connected products and access. The list may change as tools are added or removed.

ToolProductDescription
get_helpGeneral / MCP ServerReturns orientation info about the Darktrace MCP server: its purpose, tool categories, and documentation.
get_productsGeneral / MCP ServerLists available Darktrace product instances and their instance_id values needed by other tools.
submit_feedbackGeneral / MCP ServerLogs feedback about tool coverage, clarity, or usability for the Darktrace team.
count_devicesThreat VisualizerReturns the total count of devices/assets managed by Darktrace.
search_devicesThreat VisualizerSearches for devices by keyword and returns basic matching device details.
query_devicesThreat VisualizerQueries comprehensive device information using filters like IP, MAC, subnet, or SaaS module.
edit_deviceThreat VisualizerUpdates a device's label, type, priority, or notes.
get_device_activityThreat VisualizerReturns aggregated time-series data of a device's connection/data volume trends over 4 weeks.
get_detailed_eventsThreat VisualizerRetrieves individual low-level events (connections, notices, model breaches, processes) for a device or alert.
get_subnetsThreat VisualizerRetrieves monitored subnets with CIDR, device counts, DHCP status, and traffic stats.
update_subnetThreat VisualizerEdits subnet details such as label, network range, coordinates, and DHCP/exclusion flags.
get_model_alertsThreat VisualizerRetrieves model alerts (breaches) with model info, device details, and triggered components.
get_model_alert_credentialsThreat VisualizerReturns credentials seen on the device that triggered a given model alert.
update_model_alertThreat VisualizerComments on and/or acknowledges a model alert.
get_modelsThreat VisualizerRetrieves detection models with their logic, actions, and configuration.
get_incident_groupsThreat VisualizerRetrieves AI Analyst incident groups with scores, MITRE tactics, devices, and summaries.
get_incident_eventsThreat VisualizerRetrieves AI Analyst incident events with AI summaries, MITRE tactics, and breach details.
update_incident_groupThreat VisualizerComments on and/or acknowledges an AI Analyst incident group.
create_ai_analyst_investigationThreat VisualizerCreates a manual AI Analyst investigation for a device around a specified time.
get_ai_analyst_investigationsThreat VisualizerRetrieves the status and results of manual AI Analyst investigations.
advanced_searchThreat VisualizerExecutes a Lucene-syntax Advanced Search query against Darktrace log data.
get_advanced_search_syntaxThreat VisualizerReturns the full Advanced Search query syntax reference (must be called before querying).
get_response_actions_summaryThreat VisualizerReturns a summary of active and pending Autonomous Response actions and action counts over a time range.
get_endpoint_informationThreat VisualizerLooks up external endpoints (IPs/hostnames) for location, reputation, and connection history.
get_cvesThreat VisualizerRetrieves CVEs detected across assets with severity, scores, and affected devices.
get_system_healthThreat VisualizerReturns comprehensive system health metrics (CPU, memory, disk, licenses, bandwidth).
get_dam_alertsThreat VisualizerRetrieves health alerts from the Darktrace Alert Management system.
get_module_statusesThreat VisualizerRetrieves the status of Darktrace modules, optionally filtered to failing ones.
get_tagsThreat VisualizerRetrieves device tags and optionally the devices/credentials they are applied to.
manage_tagsThreat VisualizerCreates, deletes, applies, or removes tags on devices or credentials.
get_trusted_domainsThreat VisualizerRetrieves domains marked as trusted.
manage_trusted_domainsThreat VisualizerAdds or removes a trusted domain entry.
get_watched_domainsThreat VisualizerRetrieves watched domains monitored for suspicious activity.
manage_watched_domainsThreat VisualizerAdds or removes watched domain entries.
get_workflow_integration_ticketsThreat VisualizerRetrieves third-party platform tickets created by Workflow Integrations for Darktrace events.
get_cloud_accountsDarktrace / HYBRID NETWORKRetrieves cloud deployment accounts and their monitoring/compliance statuses.
get_cloud_architecturesDarktrace / HYBRID NETWORKRetrieves cloud architectures with risk breakdown, cost, and asset counts.
get_cloud_assetsDarktrace / HYBRID NETWORKRetrieves cloud assets with type, service, region, and attached/associated assets.
get_cloud_asset_filtersDarktrace / HYBRID NETWORKReturns available filter fields and operators for querying cloud assets.
get_cloud_misconfiguration_alertsDarktrace / HYBRID NETWORKRetrieves cloud security misconfiguration alerts grouped by rule.
get_cloud_misconfigured_assetsDarktrace / HYBRID NETWORKRetrieves the assets affected by a specific cloud misconfiguration rule.
get_cloud_rule_informationDarktrace / HYBRID NETWORKReturns detailed rationale, remediation, and compliance mappings for a cloud security rule.
get_emailDarktrace / EMAILRetrieves detailed information about a specific email by UUID.
search_emailsDarktrace / EMAILSearches for emails using filters and a time range.
get_email_search_filtersDarktrace / EMAILReturns available email search filter definitions and values.
action_emailDarktrace / EMAILPerforms an action (hold, release, approve/reject release) on an email for specific recipients.
analyse_email_linkDarktrace / EMAILAnalyzes a URL found in an email, returning classification tags and analysis metrics.
get_email_overviewDarktrace / EMAILReturns an aggregated email dashboard overview (threats, actions, campaigns, etc.).
get_email_listsDarktrace / EMAILRetrieves email lists and their entries.
manage_email_listsDarktrace / EMAILAdds or edits email lists, and adds or removes entries within an email list.
get_email_addin_recordsDarktrace / EMAILRetrieves Inbox Analysis or Misdirected Email add-in records.
get_email_audit_logsDarktrace / EMAILRetrieves EMAIL system audit log events for a time range.
get_email_audit_log_event_typesDarktrace / EMAILReturns available audit log event types for filtering.
get_secure_ai_overviewDarktrace / SECURE AIReturns a dashboard overview of Secure AI activity (anomaly scores, sessions, prompt categories).
get_secure_ai_sessionsDarktrace / SECURE AIRetrieves monitored generative-AI sessions with risk levels and anomaly scores.
get_secure_ai_promptsDarktrace / SECURE AIRetrieves individual prompts for a Secure AI session with anomaly/risk classifications.
get_secure_ai_usersDarktrace / SECURE AIRetrieves users interacting with generative-AI apps, with risk scores and session counts.
get_secure_ai_eventsDarktrace / SECURE AIRetrieves raw events ingested by the Secure AI post-handler.
get_secure_ai_detectionsDarktrace / SECURE AIRetrieves detections raised by Secure AI models with scores and OWASP/ATLAS mappings.
get_secure_ai_response_actionsDarktrace / SECURE AIRetrieves Autonomous Response actions taken by Secure AI.
manage_secure_ai_response_actionDarktrace / SECURE AIClears, confirms, extends, or reactivates a Secure AI response action.
get_shadow_ai_dashboardDarktrace / SECURE AIReturns the Shadow AI dashboard of unsanctioned AI/LLM services detected.
get_shadow_ai_detectionsDarktrace / SECURE AIRetrieves individual Shadow AI detections for unsanctioned AI/LLM service usage.
get_forensic_investigationsDarktrace / HYBRID NETWORKRetrieves forensic investigations with status, alarm counts, and AI summaries.
get_forensic_evidencesDarktrace / HYBRID NETWORKRetrieves evidence items with alarm counts, OS details, and processing status.
get_forensic_evidence_fileDarktrace / HYBRID NETWORKReturns detailed file metadata/content (hash, strings, VirusTotal, AI description) from an evidence item.
browse_forensic_evidence_filesDarktrace / HYBRID NETWORKBrowses the filesystem of a forensic evidence item, filtering by severity, path, or name.
get_forensic_alarmsDarktrace / HYBRID NETWORKRetrieves alarms from an investigation or evidence item with severity and MITRE techniques.
get_forensic_artifactsDarktrace / HYBRID NETWORKRetrieves detection artifacts (files, hashes, processes, users, IPs, domains) from an investigation.
get_forensic_detectionsDarktrace / HYBRID NETWORKRetrieves XDR/EDR detections with MITRE ATT&CK mappings.
get_forensic_indicatorsDarktrace / HYBRID NETWORKRetrieves indicators of compromise (IOCs) from an investigation.
get_forensic_vulnerabilitiesDarktrace / HYBRID NETWORKRetrieves vulnerabilities (CVEs) with CVSS scoring and package info.
get_forensic_pipelinesDarktrace / HYBRID NETWORKRetrieves processing/acquisition pipelines with real-time status.
get_forensic_timelineDarktrace / HYBRID NETWORKRetrieves or facets timeline events from a forensic investigation.
get_forensic_search_syntaxDarktrace / HYBRID NETWORKReturns the Forensic Search query syntax reference (call before forensic timeline queries).

[related-resource]

Continue reading
About the author
Jamie Bali
Technical Author (AI) Developer
Your data. Our AI.
Elevate your network security with Darktrace AI