Connect
Optimize
Secure
Live 68 Actions
Checkmk MCP Server
for AI Agents
Connect your AI agent to StackOne's Checkmk MCP server and give it 68 MCP tools out of the box. Auth, tool execution, and security all managed.
Checkmk MCP Server
Built by 
StackOne
StackOne 
Coverage
68 Agent Actions
Create, read, update, and delete across Checkmk — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Checkmk MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Checkmk 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 Checkmk call.
Tools Discovery →What is the Checkmk MCP Server?
A Checkmk MCP server lets AI agents read and write Checkmk data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Checkmk MCP server ships with 68 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 Checkmk MCP Tools
Every action from Checkmk's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Hosts
- Create Host
Create a new host in Checkmk
- List Hosts
List all configured hosts in Checkmk
- Update Host
Update the attributes of an existing host
- Delete Host
Permanently delete a host from Checkmk
Folders
- Create Folder
Create a new folder in the monitoring tree
- List Folders
Retrieve a list of all folders
- Update Folder
Update an existing folder's title or attributes
- Delete Folder
Delete a folder from the monitoring tree
Downtimes
- List Downtimes
Retrieve all scheduled downtimes
- Delete Downtime
Delete one or more scheduled downtimes
Comments
- List Comments
Retrieve comments by collection type
- Delete Comments
Delete one or more comments
Users
- Create User
Create a new Checkmk user account
- List Users
Retrieve all Checkmk user accounts
- Update User
Update an existing Checkmk user
- Delete User
Delete a Checkmk user account
Rules
- Create Rule
Create a new rule in a specified ruleset
- List Rules
List all rules in a specified ruleset
- Update Rule
Update an existing rule by its ID
- Move Rule
Move a rule to a different position within its ruleset
- Delete Rule
Delete a rule by its ID
Host Groups
- Create Host Group
Create a new host group in Checkmk
- List Host Groups
List all host groups in Checkmk
- Update Host Group
Update an existing host group in Checkmk
- Delete Host Group
Permanently delete a host group from Checkmk
Contact Groups
- Create Contact Group
Create a new contact group in Checkmk
- List Contact Groups
List all contact groups in Checkmk
- Update Contact Group
Update an existing contact group in Checkmk
- Delete Contact Group
Permanently delete a contact group from Checkmk
Service Groups
- Create Service Group
Create a new service group in Checkmk
- List Service Groups
List all service groups in Checkmk
- Update Service Group
Update an existing service group in Checkmk
- Delete Service Group
Permanently delete a service group from Checkmk
Notification Rules
- Create Notification Rule
Create a new notification rule in Checkmk
- List Notification Rules
List all notification rules in Checkmk
- Update Notification Rule
Update an existing notification rule in Checkmk
- Delete Notification Rule
Permanently delete a notification rule from Checkmk
Other (31)
- Create Host Downtime
Schedule a downtime for one or more hosts
- Create Service Downtime
Schedule a downtime for one or more services
- Create Host Comment
Create a comment on one or more hosts
- Create Service Comment
Create a comment on one or more services
- List Monitored Hosts
Retrieve monitored hosts from the Livestatus database
- List Services For Host
Retrieve all monitored services for a specific host
- List All Services
Retrieve all monitored services across all hosts
- List Running Activations
Retrieve all currently running activations
- List Rulesets
Retrieve all available rulesets
- Move Host To Folder
Move an existing host to a different folder
- Update Service Discovery Phase
Update the discovery phase of a specific service on a host
- Delete Acknowledgement
Remove an acknowledgement from a host or service
- Show Host
Retrieve the configuration details of a single host
- Show Folder
Retrieve a single folder by its path
- Start Service Discovery
Start a service discovery run on a host
- Activate Pending Changes
Activate pending configuration changes
- Wait For Activation Completion
Wait for an activation run to complete
- Show Activation Run
Retrieve the status of an activation run
- Show Pending Changes
Retrieve all pending configuration changes
- Show Downtime
Retrieve a single downtime by ID
- Acknowledge Host Problem
Acknowledge a problem on a host or host group
- Acknowledge Service Problem
Acknowledge a problem on a service or service group
- Show Comment
Retrieve a single comment by ID
- Show User
Retrieve a single Checkmk user by username
- Show Rule
Retrieve a single rule by its ID
- Show Ruleset
Retrieve details for a specific ruleset
- Show Host Group
Retrieve details of a single host group
- Show Contact Group
Retrieve details of a single contact group
- Show Service Group
Retrieve details of a single service group
- Show Notification Rule
Retrieve details of a single notification rule
- Show Version
Retrieve Checkmk server version information
Set Up Your Checkmk MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Checkmk 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>"
]
}
}
}Platform 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
Checkmk MCP Server FAQ
Does StackOne have a Checkmk MCP server?
Yes. StackOne offers a hosted Checkmk MCP server with 68 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.
Checkmk MCP server vs direct API integration — what's the difference?
A Checkmk MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Checkmk. A Checkmk 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 Checkmk at runtime. StackOne provides both.
How does Checkmk authentication work for AI agents?
Checkmk 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 Checkmk account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Checkmk MCP tools vulnerable to prompt injection?
Yes — Checkmk 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 Checkmk agent and how do I avoid it?
Context bloat happens when Checkmk tool schemas and API responses eat your Checkmk agent's memory, preventing it from reasoning effectively. A single Checkmk 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 Checkmk agent can access?
Yes — you can limit which actions your Checkmk 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 Checkmk MCP server?
Yes — you can create custom agent actions for your Checkmk MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Checkmk's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Checkmk MCP server?
Skip a Checkmk MCP server if your integration is purely software-to-software — direct Checkmk 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 Checkmk actions at runtime.
What AI frameworks and AI clients does the StackOne Checkmk MCP server support?
The StackOne Checkmk 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.