wsltop
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Read-only local observations. Preserve snapshot_id across calls; resource IDs are opaque and observation-scoped. CPU percentages use the collected host-wide scale. Environment and parent/child usage can overlap; do not sum them. No actions or shell tools.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_system_summaryA | Start CPU or memory diagnosis here: get observed host and environment CPU/memory state plus snapshot metadata. Usage can overlap; do not sum it. Null does not imply zero usage. Do not infer paging, disk I/O, or memory-pressure causality from memory usage alone. |
| list_resourcesA | Find processes, applications, containers, or infrastructure by CPU/memory, filters, and limit. Reuse snapshot_id for follow-ups; resource IDs belong to that observation. Use returned hierarchy for attribution; do not infer container membership from process names or source labels alone. |
| inspect_resourceA | Inspect details of a resource found by list_resources or list_children. Pass its returned resource_id together with the same snapshot_id. |
| list_childrenA | Drill into a container, application, or attribution hierarchy's immediate children. Pass the parent's resource_id and the same snapshot_id; child usage overlaps parent usage. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool targets a distinct action: summary overview, resource search, resource details, and hierarchy drill-down. Even the two 'list' tools are clearly separated by noun (resources vs children), so no ambiguity exists.
All tool names follow a consistent verb_noun snake_case pattern (get_, list_, inspect_, list_). The two list_ tools are differentiated by their nouns, preserving a predictable naming scheme.
With 4 tools, the set is tightly scoped for a read-only system monitoring workflow. Each tool fills a necessary role in the exploration process without redundancy or bloat.
The tools cover the full exploratory lifecycle: overview (get_system_summary), discovery (list_resources), detail (inspect_resource), and hierarchical navigation (list_children). No obvious operations are missing for the stated purpose.