CICD AIops MCP server

<!-- mcp-name: io.github.AIops-tools/cicd-aiops -->

CICD AIops

Governed AI-ops for self-managed GitLab and self-hosted Gitea.

cicd-aiops is for the team running its own CI/CD forge — a GitLab instance or a Gitea server on your hardware, in your lab, behind your VPN — who want an AI agent that can answer "why did the pipeline fail?", "which runner is wedged?", "where did 40 GB of artifact storage go?" and "what work went stale?" and then act (retry, cancel, pause, delete, protect) only through an audited, budgeted, risk-tiered, undo-recorded governance harness. It is not a SaaS integration: it speaks the GitLab REST API v4 and the Gitea API v1 directly against your server, with credentials encrypted at rest.

Verification status: modelled from each project's public API docs and

exercised against mocked HTTP responses; there is no recorded end-to-end run

against a live server yet. cicd-aiops doctor is the fastest live check —

see docs/VERIFICATION.md.

Routing: Do NOT use this for Kubernetes deploy state — use k8s-aiops.

This tool ends at the CI/CD server's API (pipelines, runners, artifacts,

repo hygiene).

What this tool does, and does not, decide

It delivers CI/CD operations — reads and writes — accurately and efficiently, and records every one of them. It does not decide whether a write is allowed to happen. That is the agent's judgement, or the permission of the token you connect it with: give it a GitLab/Gitea access token without write scope and the writes fail at the server — the place that actually owns the permission.

So there is no read-only switch, no policy file, no approval gate to configure. The one thing the tool guarantees is that nothing is silent: every call, over MCP and over the CLI alike, lands an audit row in ~/.cicd-aiops/audit.db, and destructive writes still capture their before-state and record an inverse where one exists.

Each tool declares a risk_level, kept in agreement with its [READ]/[WRITE]

documentation tag by a test, and carried into the audit row as a descriptive

tier — so a reviewer can see at a glance that a row was a high-risk delete. It

is a label, not a gate.

Running a smaller / local model? See agent-guardrails.md — it lists the guardrails this tool enforces for you (so you don't spend prompt budget restating them) and gives a ready-made system prompt for what's left.

Quick start

As a Claude Code plugin

One install gives an agent both the skill and the MCP server:

/plugin marketplace add AIops-tools/marketplace
/plugin install cicd-aiops@aiops-tools

The MCP server is fetched with uv and pinned to the package version this plugin declares, so an audit row can be traced back to the code that wrote it. Credentials are still configured with cicd-aiops init — see below.

As an OpenClaw plugin

The same bundle is published on ClawHub, where one install delivers the skill and its MCP server together:

openclaw plugins install clawhub:@zw008/cicd-aiops
openclaw skills info cicd-aiops          # expect: Visible to model: yes

Restart the OpenClaw gateway afterwards so it loads the plugin. The MCP server is fetched with uv, pinned to this exact release, so uvx has to be on PATH — without it the skill still installs but reports Visible to model: no. Credentials are configured exactly as below.

As a CLI or standalone MCP server

uv tool install cicd-aiops        # or: pip install cicd-aiops

cicd-aiops init        # wizard: base URL + token (encrypted) + TLS verify
cicd-aiops doctor      # connectivity + token-scope probe per target
cicd-aiops overview    # version, identity, projects, runners at a glance

Then the interesting parts:

Shortened. The full README is on GitHub.