The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the OpenITCOCKPIT listing page.
An MCP server that puts an openITCOCKPIT monitoring instance in front of an LLM client: what is broken and why, what someone already handles, what changed - and, off by default, the tools that act on it.
[!CAUTION] Use at your own risk. This server lets a language model read and - with write tools enabled - change your monitoring configuration. A model can misunderstand a request or pick the wrong call. Review what it proposes before you approve it, and start with read-only access. The software is provided "as is", without warranty or liability of any kind; see the MIT License.
Point your client at http://localhost:8000/mcp with the bearer token from your
.env. Compose reads that same file for the published port, so setting
OITC_PORT there moves both sides at once.
Three settings matter to start: MCP_AUTH_TOKEN (what clients present to this
server), OITC_BASEURL and OITC_APIKEY (what this server presents to
openITCOCKPIT). Everything else has a default -
all of it.
| Ask | What answers it |
|---|---|
| "What is broken right now?" | get_problem_overview - causes separated from their consequences |
| "Why is db-01 critical?" | get_service_health, investigate_problem |
| "Is anyone on it already?" | the same tools: downtime and acknowledgement come with the state |
| "What happened during the night shift?" | get_shift_summary |
| "Why did I get no alert for web01?" | explain_notification |
| "Take web01 out until Monday" | schedule_downtime (write) |
| "Which templates could web-05 use?" | get_allowed_elements_for_container |
Every tool by name, with its parameters and what it costs in context: docs/tools.md, generated from the code. What a result looks like and what happens when you write: docs/using-the-tools.md.
Running a monitoring instance is not one job, so a surface small enough to be easy would be too small to be useful. Instead the server keeps every tool the work needs and a toolset hands one agent its share: around ten tools, complete for that job and nothing beyond it. A tool that was never registered cannot be called at all.
The shipped sets are health, operations, lifecycle, patch, reporting,
catalog, onboarding, config and provisioning. Sets are defined in a file
you can replace: docs/toolsets.md.
oitc-mcp-eval asks operator questions against your instance and checks whether
a model answers them from the tools instead of inventing. It keeps every run in
SQLite, so models and changes stay comparable.
| Configuration | every setting, and which secret goes where |
| Connecting a client | HTTP and stdio, with working examples |
| Installation | Docker, from source, MCP Registry |
| Tools | every tool, generated from the code |
| Working with the tools | result shapes, container scope, read-modify-write |
| Toolsets | limiting an instance, writing your own set |
| Skills and prompts | the material served alongside the tools |
| Measuring a model | the eval, its cases, and reading the results |
| Security | what this server can reach, and what it refuses |
| Architecture | how the pieces fit together |
| Tool design | the rules a new tool follows |
| openITCOCKPIT API notes | the behaviour this server works around |
| Versioning | version numbers and compatibility |
| Development | checks, tests, running from a checkout |
The server holds one openITCOCKPIT credential and never sends it to a client. Clients authenticate with their own token; in delegated mode each request carries a short-lived user token instead, and the server acts as that user with their permissions. Write tools stay unregistered until you enable them. The details, including what to give the openITCOCKPIT user: docs/security.md.
MIT.