From infrahub
Analyzes live Infrahub data via MCP server to answer operational questions, detect drift, check compliance, investigate change impact, and produce ad-hoc reports.
npx claudepluginhub opsmill/claude-marketplace --plugin infrahubThis skill is limited to using the following tools:
Expert guidance for interactive data analysis
Provides shared references for Infrahub skills: GraphQL query syntax and patterns, .infrahub.yml config format, caching rules, Python env checks, Git integration.
Manages hosts, groups, and variables in Ansible inventory files using INI and YAML formats for infrastructure organization across environments.
Manages physical server infrastructure and bare metal systems with iDRAC/iLO/IPMI access, SSH connectivity checks, boot time estimation, and hardware health monitoring.
Share bugs, ideas, or general feedback.
Expert guidance for interactive data analysis against a live Infrahub instance. This skill uses the Infrahub MCP server to query, correlate, and reason over infrastructure data on demand — answering operational questions that span multiple node types and relationships.
Use this skill for any question of the form "what does Infrahub currently know about X, and how does it relate to Y?"
Typical question patterns:
For automated, pipeline-enforced checks that
block proposed changes, see
../infrahub-managing-checks/SKILL.md.
For repeatable scheduled reports exported as
artifacts, see ../infrahub-managing-transforms/SKILL.md.
If invoked with arguments (e.g., /infrahub:analyzing-data Which devices have no platform assigned?),
treat the arguments as the question to answer.
The Infrahub MCP server exposes tools that let Claude query Infrahub data directly. The typical workflow:
| Priority | Category | Prefix | Description |
|---|---|---|---|
| CRITICAL | MCP Tools | mcp- | Available Infrahub MCP tools, invocation patterns, response structure |
| CRITICAL | Query Patterns | query- | GraphQL structures for fetching, filtering, and traversing relationships |
| HIGH | Correlation | correlation- | Joining, diffing, and reasoning over data from multiple queries |
| HIGH | Reporting Output | reporting- | Presenting findings: summaries, tables, per-object detail, remediation hints |
| MEDIUM | Approach Selection | approach- | When to use MCP analysis vs InfrahubCheck vs Transform |
When the Infrahub MCP server is connected, Claude can call tools such as:
mcp__infrahub__infrahub_query — Execute a
GraphQL query (primary tool)mcp__infrahub__infrahub_list_schema — List
available node kindsmcp__infrahub__infrahub_get — Retrieve a
specific object by ID or filtersmcp__infrahub__infrahub_create — Create an
object (remediation, on a branch)mcp__infrahub__infrahub_update — Update an
object (remediation, on a branch)# Example: find all devices in an active
# maintenance window
query MaintenanceDevices {
MaintenanceWindow(status__value: "active") {
edges {
node {
name { value }
start_time { value }
end_time { value }
devices {
edges {
node {
name { value }
role { value }
site {
node { name { value } }
}
}
}
}
}
}
}
}
1. Understand the question
→ "Which services depend on devices currently
in a maintenance window?"
2. Identify the node types involved
→ MaintenanceWindow, DcimDevice, Service
(or equivalent in your schema)
3. Query current state
→ mcp__infrahub__infrahub_query — one query
per node type, or combined
4. Correlate the data
→ Join across node types, filter, count, diff
5. Report findings
→ Summarize with counts, list affected objects,
suggest next steps