Model Context Protocol server for Liongard configuration management integration, providing tools for interacting with Liongard API across multiple domains including environments, agents, inspections, systems, detections, metrics, timeline, and inventory.
Strong tool coverage (24 tools across 8 domains) with explicit schemas and descriptions for all tools. Naming follows verb_noun convention consistently. Most descriptions are clear and actionable (average ~150 chars, within the 10-1024 baseline). All tools have typed input schemas with required field declarations. However, output schemas are not explicitly documented in the source code provided, and parameter descriptions vary in depth. Error handling guidance is minimal. Tool composition is well-organized by domain. The liongard_navigate discovery tool is a positive UX pattern. One destructive tool (liongard_agents_delete) includes a warning annotation.
⚠ DESTRUCTIVE — IRREVERSIBLE. Permanently deletes an agent from Liongard and removes all associated monitoring data and configurations. This action cannot be undone. Confirm with the user before invoking.
List agents in Liongard with pagination. Agents are installed on-premise to facilitate inspections and data collection.
Get detailed information about a specific detection by its ID via GET /api/v1/detections/{id}.
List detections in Liongard via POST /api/v2/detections. Defaults to the last 30 days; pass startDate/endDate (ISO-8601) to override the date range. Returns a paginated envelope with `Data` and `Pagination`.
Get the total count of environments in Liongard. Useful for understanding the size of your environment inventory.
Output schemas not documented in source code. While input schemas are properly typed and visible, return value structures are not explicitly specified, forcing LLMs to infer field names and types from raw API responses.
Pagination defaults not specified for all list tools. While page and pageSize parameters exist, descriptions do not state default values (e.g., 'default: page=1, pageSize=50') or max limits, leaving LLMs uncertain whether to paginate automatically.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | B | 75 | 2026-07-28+ | v2 |
Create a new environment in Liongard. Only Name is required, all other fields are optional.
Get detailed information about a specific environment by its ID. Returns full environment profile including status, visibility, and tier.
List environments (customers/companies) in Liongard with pagination. Returns environment details including name, status, and tier.
Get related entities for a specific environment. Returns associated launchpoints, agents, integration mappings, and child environments.
Create a new launchpoint (configured inspection instance). Requires an inspector ID, environment ID, and a name.
List available inspectors (inspection types) in Liongard with pagination. Inspectors define what data is collected.
List launchpoints (configured inspection instances) in Liongard with pagination. Launchpoints are configured instances of inspectors tied to environments.
Trigger an immediate inspection run for a specific launchpoint. The inspection will execute as soon as possible.
Get detailed information about a specific device profile by its ID. Returns full device profile details.
List device profiles in Liongard for a specific environment. Device profiles represent hardware and software assets discovered through inspections. Use liongard_environments_list to find environment IDs.
List asset identities in Liongard for a specific environment. Identities represent users, accounts, and other identity entities discovered through inspections. Use liongard_environments_list to find environment IDs.
Get detailed information about a specific identity by its ID. Returns full identity profile.
Evaluate a metric across all systems in an environment. Returns the evaluation results showing compliance or configuration status.
Evaluate a metric for a specific system. Returns the evaluation result showing compliance or configuration status for that system.
List available metrics in Liongard that can be evaluated across systems. Metrics define configuration or compliance checks.
Discover available Liongard tools by domain. Returns tool names and descriptions for the selected domain. All tools are callable at any time — this is a help/discovery aid, not a prerequisite.
Get detailed information about a specific system by its ID. Returns full system profile including discovered properties and attributes.
List infrastructure components (systems) discovered through inspections, with pagination. Systems represent discovered devices, servers, and infrastructure elements.
List inspection events and configuration changes in chronological order. Returns a timeline of discoveries and detections.
Error handling and recovery guidance absent. No tool descriptions explain what errors might occur (e.g., 'environment not found', 'invalid metric ID') or how to recover. Descriptions lack actionable guidance per pattern:recovery-guide.
Destructive tool (liongard_agents_delete) lacks confirmation/dry-run mechanism. Tool warns '⚠ DESTRUCTIVE, IRREVERSIBLE' but provides no dry-run variant or confirmation step. LLMs cannot safely preview impact before executing.
Parameter descriptions for optional/required fields inconsistent. Some tools (e.g., liongard_environments_create) do not indicate which fields are truly optional vs required in parameter descriptions, only in JSON schema 'required' array, which LLMs may not parse reliably.