ContraForce
ContraForce offers Security Delivery Agents for MSPs and MSSPs on Microsoft Defender XDR and Sentinel that triage, investigate, respond and report across customer tenants, with approval gates on high-impact actions.
ContraForce is an agentic security delivery platform for MSPs, MSSPs and security operations teams working in Microsoft Defender XDR and Microsoft Sentinel. Its Security Delivery Agents run the delivery loop across customer tenants: triage, investigation, evidence gathering, response, ticketing and customer reporting. The agent can run automatically on every incident of a chosen severity, inside weekly working hours set with Agent Shifts, or when an analyst starts it.
Customers upload their own classification and response operating procedures to an SOP Knowledge Base scoped to each workspace, and the agent follows them. Response actions such as Isolate Endpoint, Reset User Password, Lockout User, Quarantine File, Block Cloud IP and Delete Email run through Gamebooks, where ordered run policies block an action, allow it or send it to a named approver first, and the agent leaves actions to an analyst when its confidence is below a set threshold.
Every agent decision, action and approval gate is logged, and execution history shows each run's trigger, outcome, token counts and cost. Customers choose the AI model when they create an agent, from the models offered in their region. The platform is cloud hosted with US and UK regional deployments. It holds SOC 2 Type II certification, is aligned to ISO 27001:2022, offers SSO and audit logs on every plan, and publishes a v2 REST API with webhooks. Integrations include Defender XDR, Sentinel, SentinelOne, CrowdStrike, Autotask, ServiceNow, Jira and Azure Lighthouse.
Vendor details
Canonical URL
https://www.contraforce.com
Category
Security / SOC agent
Funding status
ContraForce is private and at seed stage. It was founded in 2021 in McKinney, Texas by Stan Golubchik and Ricky Melendez, and raised a 3.25 million dollar seed round co-led by GALLOS Ventures and DataTribe, with Y Combinator participation.
Company status
independent
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
ContraForce integrates with Microsoft Defender XDR, Microsoft Sentinel, Defender for Endpoint, Entra ID, SentinelOne, CrowdStrike, Autotask, ServiceNow, Jira and Azure Lighthouse, and offers a v2 REST API and webhook events, including an agent investigation completed webhook. There is no MCP server.
In practice
A managed security provider wants incidents handled overnight without waking an analyst. ContraForce's Security Delivery Agent runs on every incident of a set severity during its Agent Shifts, investigating and taking response actions in tools such as Microsoft Defender XDR, SentinelOne and CrowdStrike.
Isolating an endpoint or resetting a password should not happen without sign off. Gamebook run policies send those high impact actions to a named approver first, and every decision, action and approval is logged with full attribution.
A security team wants the agent to follow its own procedures, not generic ones. It uploads its classification and response procedures to the SOP Knowledge Base, starts with investigation only runs, and widens autonomy one Gamebook at a time as the verdicts hold up.
Sources & related URLs
Related / legacy domains
Agentic Index coverage score
11.0 / 14 capabilities · 79%
| Integrations & Tool Calling | Full |
|---|---|
|
Named integrations cover Microsoft Defender XDR, Microsoft Sentinel, SentinelOne, CrowdStrike, Autotask, ServiceNow, Jira and Azure Lighthouse, and the agent takes response actions in them such as Isolate Endpoint, Reset User Password, Lockout User, Quarantine File, Block Cloud IP and Delete Email. Sourcecontraforce.com/platformread 2026-09-28 |
|
| Workflow Orchestration | Full |
|
Security Delivery Agents run the delivery loop from triage and investigation through response, ticketing and customer reporting. Customers shape the flow, with uploaded response operating procedures setting the containment and remediation steps, settings per severity and classification deciding what runs automatically, and ordered Gamebook run policies blocking, allowing or routing each action. Sourcedocs.contraforce.com/guides/getting-started/configuring-security-delivery-agentsread 2026-09-28 |
|
| Knowledge Grounding & RAG | Full |
|
ContraForce grounds the agent in an SOP Knowledge Base, where customers upload classification and response operating procedures as Markdown or text, versioned by re-upload and scoped per workspace, for the agent to draw on in each incident. An Entity Context Graph of the incident's users, devices and IPs sits alongside it. Sourcedocs.contraforce.com/guides/agent-center/operating-proceduresread 2026-09-28 |
|
| Human Oversight & Guardrails | Full |
|
Gamebook run policies are ordered rules that block an action, allow it or send it to an approver first, and high-impact actions such as Isolate Endpoint and Reset User Password sit behind a named approver. Below a confidence threshold, the agent leaves actions to an analyst. Sourcedocs.contraforce.com/guides/getting-started/what-are-gamebooksread 2026-09-28 |
|
| Security, Identity & Governance | Full |
|
SSO and audit logs come on every plan, alongside SOC 2 Type II certification, alignment to ISO 27001:2022, SCIM provisioning on Scale, user roles and permissions and federated least-privilege access. Sourcecontraforce.com/pricingread 2026-09-28 |
|
| Observability & Auditability | Full |
|
Every decision the agent makes, every action it takes and every approval gate is logged with full attribution. Agent Execution History records each run's trigger, incident, source, outcome and prompt, along with cached and completion token counts and USD cost, so each run has its own record. Sourcedocs.contraforce.com/guides/agent-center/agent-execution-historyread 2026-09-28 |
|
| Memory & State Persistence | Not documented |
|
The agent has no memory with a set scope and lifetime, and no context engine or remediation snapshots are described. The SOP Knowledge Base grounds the agent but is not memory. Sourcedocs.contraforce.com/guides/agent-center/operating-proceduresread 2026-09-28 |
|
| Deployment & Data Residency | Full |
|
Deployments run in the US and the UK, with customer data processed and stored only within the assigned regional deployment, a UK-resident stack and Data Zone Standard model deployments offered by region. An EU deployment is planned, and no self-hosted or customer-hosted deployment is offered. Sourcecontraforce.com/platformread 2026-09-28 |
|
| Prebuilt Agents / Templates / Packs | Partial |
|
ContraForce ships one prebuilt agent type, the Security Delivery Agent, deployed per workspace, plus a fixed catalog of response actions. Gamebooks are assembled per incident from those actions, with no named template library, and the procedures are the customer's own uploads. Sourcedocs.contraforce.com/guides/getting-started/what-are-gamebooksread 2026-09-28 |
|
| Triggers & Channel Coverage | Full |
|
The On Queue setting runs the agent automatically on every incident of a configured severity, and Agent Shifts set the weekly hours in which it investigates on its own. Manual runs remain available. Sourcedocs.contraforce.com/guides/agent-center/agent-shiftsread 2026-09-28 |
|
| Model Flexibility & Routing | Full |
|
When creating a Security Delivery Agent, the customer chooses the AI model and deployment type (Global Standard or Data Zone Standard) from the models available in the Agent Center's region, with upgrades to GPT-5.5 and GPT-5.6 depending on runtime support. Sourcedocs.contraforce.com/release-notesread 2026-09-28 |
|
| APIs / SDKs / MCP Extensibility | Full |
|
Every plan includes a v2 REST API at portal.contraforce.com/api/v2, with service account Basic auth and workspace, cross-workspace and organization scoped endpoints for incidents, gamebooks, tickets, data sources and analytics rules, plus a webhook event reference that includes an agent investigation completed webhook. There is no MCP server. Sourcedocs.contraforce.com/api-reference/endpointsread 2026-09-28 |
|
| Testing, Debugging & Optimization | Partial |
|
Rollout starts with investigation-only runs before response actions are enabled, and autonomy then expands one Gamebook at a time as verdicts hold up, which works as a dry-run style check on the agent's own output. There is no scored test harness. Sourcedocs.contraforce.com/guides/getting-started/configuring-security-delivery-agentsread 2026-09-28 |
|
| Browser / Computer-use | Not documented |
|
The agent acts through API integrations, and browser or computer use is not described. Sourcecontraforce.com/platformread 2026-09-28 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Recent platform changes
ContraForce added email alerts when an agent investigation assigns an incident a malicious score at or above a configured threshold. Teams can choose recipients, change the default threshold of 80, and restrict alerts to selected incident severities. Each incident generates at most one such email even if the agent investigates it again.
Bears on: Human approval / guardrails
View sourceContraForce expanded its audit trail to cover Standard Operating Procedure (SOP) and security rule changes. The SOP Center now features a dedicated Audit tab that records the creation, updating, deletion, and linking of SOPs, as well as the enabling or disabling of security rules.
Bears on: Observability / auditability
View sourcePricing
Starter from $249 per month (4 client workspaces), plus a flat rate per incident for each agent run, quoted by ContraForce.
Monthly tier by client workspace allowance, plus a flat rate per Security Delivery Agent run.
Included quota
Starter includes 4 client workspaces, Growth 30 and Scale 85. No agent runs are included.
Cost watchouts
The per incident run rate is quoted, not published, so run costs scale with incident volume and are unknown up front. Extra workspaces are $50 per month each.
Variable cost rationale
The monthly tier fee is flat and sets the client workspace allowance. Every Security Delivery Agent run is metered at a flat rate per incident, with no included runs, so the bill grows with incident volume across client tenants. Extra workspaces add $50 per month each. No cap on runs is published, and the per incident rate is quoted rather than listed. Plans run month to month, and annual prepay takes 15% off the plan fee.
Overage / add-ons
There are no included runs and no overage tiers. Every Security Delivery Agent run is billed at a flat rate per incident, pay as you go. Extra workspaces are $50 per month each.
Sales call required
Mixed (some tiers require a call)
Free / trial
30 day trial of 250 investigations or 30 days, whichever comes first, across up to 4 workspaces, with no card required
Lowest paid plan
Starter at $249 per month with 4 client workspaces
Key ambiguities
The per incident run rate is not published. ContraForce quotes it directly.
Cancellation / refund
Plans run month to month with no long term commitment, and annual prepay takes 15% off the plan fee. Enterprise terms are quoted by sales.
Support SLA / resale
Scale includes business priority support. Support levels on Starter and Growth are not published.
Related vendors
- 7AI — Agentic SOC from the Cybereason founders: domain specialized agents…
- Abnormal AI — Behavioral AI email security with three named autonomous agents: a…
- AirMDR — AI native MDR whose AI analyst investigates every alert and writes…
- Airrived — Agentic OS that unifies SOC, GRC, IAM, vulnerability management, IT,…
- Andesite — Human-AI SOC platform where customers build their own agents and…
- Anvilogic — Agentic security operations platform that works on top of existing…
Alternatives to ContraForce
The closest documented capability profiles to ContraForce among security and SOC agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- CrowdStrike12.0 / 14Adds documented Memory & State Persistence
- Arctic Wolf9.5 / 14A lighter documented profile than ContraForce
- D3 Security (Morpheus)10.5 / 14Adds documented Memory & State Persistence
- Drata10.5 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs
- Palo Alto Networks10.5 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs
- SentinelOne10.5 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded