NetPulse
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.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ping_deviceA | Ping a network device and return round-trip time statistics. Args: target: IP address or hostname to ping. count: Number of ping packets to send (1-20, default 5). |
| run_tracerouteA | Run a simulated traceroute to a network device. Args: target: IP address or hostname of the destination. max_hops: Maximum number of hops (1-64, default 30). |
| check_interfaceB | Get detailed diagnostic information for a specific interface. Args: device: Hostname of the network device. interface: Interface name (e.g., GigabitEthernet0/0). |
| get_device_configA | Retrieve the running configuration of a network device (read-only). Args: device: Hostname of the network device. section: Config section (e.g., 'bgp', 'ospf'). Returns full config if empty. |
| compare_baselineA | Compare a device's current metric value against its rolling baseline. Args: device: Hostname of the network device. metric: Metric name (cpu_percent, memory_percent). window: Baseline window (for display context, default '24h'). |
| restart_interfaceA | Restart (bounce) a network interface. REQUIRES explicit confirmation. This is a state-modifying action. You MUST set confirm=true to execute. If confirm is false or missing, an impact analysis is returned instead. Args: device: Hostname of the network device. interface: Interface name to restart (e.g., GigabitEthernet0/0). confirm: Must be explicitly set to true to execute the restart. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| network_health_summary | Generate a comprehensive network health briefing. Reads all available resources and produces a structured NOC briefing with overall health score, devices requiring attention, bandwidth utilization trends, active incidents, and recommended actions. |
| troubleshoot_connectivity | Diagnose connectivity issues between two network endpoints. Args: source: Source device hostname or IP. destination: Destination device hostname or IP. |
| capacity_planning | Analyze bandwidth utilization and project capacity needs. Reads bandwidth and interface data to identify links approaching capacity limits and recommend upgrade timelines. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| device_status | Returns status of all monitored network devices with summary counts. |
| latency_report | Returns ping latency matrix between all monitored endpoints with threshold context. |
| bandwidth_top_talkers | Returns top 10 bandwidth consumers by source/destination. |
| topology_map | Returns network topology as nodes and edges with health status per link. |
| active_alerts | Returns all currently firing alerts with severity, source, and duration. |
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose: ping and traceroute for connectivity tests, interface diagnostics, config retrieval, baseline comparison, and interface restart. No overlap in functionality.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., ping_device, run_traceroute, check_interface), with no mixing of styles or vague verbs.
With 6 tools, the server is well-scoped for network diagnostic and management tasks. Each tool serves a distinct purpose without unnecessary bloat or gaps.
The set covers core network operations: connectivity test, path tracing, interface diagnostics, config retrieval, metric comparison, and a management action. Missing features like device listing or interface statistics are minor gaps for the intended domain.