Connect
Optimize
Secure
InfoSec MCP Server
for AI Agents
Production-ready InfoSec MCP server with 30 extensible actions — plus built-in authentication, security, and optimized execution.
InfoSec MCP Server
Built by 
StackOne
StackOne 
Coverage
30 Agent Actions
Create, read, update, and delete across InfoSec — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your InfoSec MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every InfoSec 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 InfoSec call.
Tools Discovery →What is the InfoSec MCP Server?
A InfoSec MCP server lets AI agents read and write InfoSec data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's InfoSec MCP server ships with 30 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All InfoSec MCP Tools and Actions
Every action from InfoSec's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Campaigns
- List Campaigns
Retrieve a list of all training campaigns
- Get Campaign
Retrieve detailed information for a specific campaign
Campaign Runs
- List Campaign Runs
Retrieve all runs for a specific campaign
- Get Campaign Run
Retrieve details for a specific campaign run
Courses
- List Courses
Retrieve a list of all training courses
- Get Course
Retrieve details for a specific course by ID
Learner Groups
- List Learner Groups
Retrieve a list of all learner groups
- Get Learner Group
Retrieve details for a specific learner group
Learners
- Create Learner
Create a new learner in the account
- List Learners
Retrieve a list of all learners in the account
- Get Learner
Retrieve detailed information for a specific learner by ID
- Update Learner
Update an existing learner's information
- Delete Learner
Delete a learner from the account
PhishSim Templates
- List PhishSim Templates
Retrieve a list of all PhishSim phishing templates
- Get PhishSim Template
Retrieve details for a specific PhishSim template
PhishHunter Messages
- List PhishHunter Messages
Retrieve a list of reported phishing emails from PhishHunter
- Get PhishHunter Message
Retrieve details for a specific PhishHunter reported message
Other (13)
- Get Assessment
Retrieve details for a specific assessment by ID
- List Phishing Batteries
Retrieve a list of all PhishSim template batteries
- List Campaign Run Learners
Retrieve learners enrolled in a campaign run
- Get Campaign Run Statistics
Retrieve statistics for a campaign run
- Get Module
Retrieve details for a specific training module by ID
- List Learner Group Members
Retrieve learners belonging to a specific group
- Get Learner Timeline Events
Retrieve timeline events for a specific learner
- List Notifications
Retrieve a list of all notification templates
- Get Quarantined Email
Retrieve details for a specific quarantined email
- List Categories
Retrieve a list of all training categories
- List Languages
Retrieve a list of all available languages
- List Timeline Events
Retrieve organization-wide timeline events
- Enroll Learner In Campaign
Enroll a learner into a specific campaign
Set Up Your InfoSec MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to InfoSec in under 10 lines of code.
MCP Clients
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>"
]
}
}
}More Security MCP Servers
Cloudflare
137+ actions
OneLogin
109+ actions
Sentinel XS
69+ actions
Microsoft Entra ID
67+ actions
Drata
57+ actions
JumpCloud
53+ actions
Rippling
37+ actions
InfoSec MCP Server Resources
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
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
InfoSec MCP Server FAQ
InfoSec MCP server vs direct API integration — what's the difference?
A InfoSec MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling InfoSec. A InfoSec MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling InfoSec at runtime. StackOne provides both.
How does InfoSec authentication work for AI agents?
InfoSec authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own InfoSec account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are InfoSec MCP tools vulnerable to prompt injection?
Yes — InfoSec MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a InfoSec agent and how do I avoid it?
Context bloat happens when InfoSec tool schemas and API responses eat your InfoSec agent's memory, preventing it from reasoning effectively. A single InfoSec query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my InfoSec agent can access?
Yes — you can limit which actions your InfoSec agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my InfoSec MCP server?
Yes — you can create custom agent actions for your InfoSec MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research InfoSec's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a InfoSec MCP server?
Skip a InfoSec MCP server if your integration is purely software-to-software — direct InfoSec API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call InfoSec actions at runtime.
What AI frameworks and AI clients does the StackOne InfoSec MCP server support?
The StackOne InfoSec MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.
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.