Defense.com MCP Server
for AI Agents
Connect your AI agent to StackOne's Defense.com MCP server and give it 22 MCP tools out of the box. Auth, tool execution, and security all managed.
StackOne 
Coverage
22 Agent Actions
Create, read, update, and delete across Defense.com — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Defense.com MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Defense.com tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Defense.com call.
Tools Discovery →What is the Defense.com MCP Server?
A Defense.com MCP server lets AI agents read and write Defense.com data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Defense.com MCP server ships with 22 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All Defense.com MCP Tools
Every action from Defense.com's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Companies
- List Companies
List the client companies managed under a partner account.
Companys
- Create Company
Create a client company under a partner account.
- Get Company
Retrieve a single managed client company.
Attach Managed Company Source Documents
- Attach Managed Company Source Document
Attach a document to an external threat source on a managed company.
Threat Detections
- List Threat Detections
List the individual detection events rolled up under a threat.
Attach External Source Documents
- Attach External Source Document
Attach a report-level document to an external threat source.
Managed Company Threats
- Create Managed Company Threat
Create a threat on a managed client company.
Threat Notes
- Create Threat Note
Add an investigation note to a threat.
- List Threat Notes
Retrieve all investigation notes on a threat.
- Update Threat Note
Update an existing note on a threat.
Packages
- List Packages
List the product packages available to a partner.
Threat Remediations
- List Threat Remediations
List the remediation actions attached to a threat.
- Get Threat Remediation
Retrieve a single remediation on a threat.
- Update Threat Remediation
Update a remediation's assignee or state.
Threat Assets
- List Threat Assets
List the assets affected by a threat.
Threat Detection Assets
- List Threat Detection Assets
List the assets affected by a specific detection.
Threat Detection Users
- List Threat Detection Users
List the users affected by a specific detection.
Threat Users
- List Threat Users
List the users affected by a threat.
Threats
- Create Threat
Create or aggregate a threat from an external security source.
- List Threats
Retrieve a paginated list of threats detected on the account.
- Get Threat
Retrieve a single threat by its identifier.
- Update Threat
Update a threat's remediation assignment or state.
Set Up Your Defense.com MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Defense.com in under 10 lines of code.
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}Defense.com Resources
Closing the Loop: A Self-Evolving Defense
How we built an autonomous loop that discovers new prompt injection techniques, scores them against real models and Defender, and files a PR back to the package
8 min read
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
MCP vs A2A: Architecture, Security, and When to Use Each
MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.
12 min
MCP vs API: What Hundreds of Connector Builds Taught Us
MCP wraps APIs, it doesn't replace them. After building hundreds of connectors that serve both, here's when each approach wins.
14 min read
Defense.com MCP Server FAQ
Does StackOne have a Defense.com MCP server?
Defense.com MCP server vs direct API integration — what's the difference?
How does Defense.com authentication work for AI agents?
origin_owner_id.Are Defense.com MCP tools vulnerable to prompt injection?
What is the context bloat of a Defense.com agent and how do I avoid it?
Can I limit which actions my Defense.com agent can access?
Can I create custom agent actions for my Defense.com MCP server?
When should I NOT use a Defense.com MCP server?
What AI frameworks and AI clients does the StackOne Defense.com MCP server support?
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.