NetPulse
Provides pre-configured dashboards for visualizing network performance and health metrics.
Exposes network telemetry metrics at a /metrics endpoint for Prometheus to scrape and alert on.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@NetPulseGive me a network health summary"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
NetPulse π
An MCP server that exposes live network monitoring data as Resources and diagnostic capabilities as Tools, letting AI assistants query network health conversationally.
NetPulse bridges the gap between traditional network monitoring and AI-powered operations. It implements the Model Context Protocol (MCP) to give AI assistants like Claude real-time access to network telemetry β device status, interface metrics, latency measurements, bandwidth utilization, and active alerts β all through a clean, structured API.
Architecture
graph TB
subgraph "AI Layer"
Claude["Claude Desktop / MCP Client"]
end
subgraph "NetPulse MCP Server"
Server["server.py<br/>FastMCP"]
Resources["Resources<br/>6 data endpoints"]
Tools["Tools<br/>6 diagnostic actions"]
Prompts["Prompts<br/>3 workflow templates"]
Sim["Network Simulator<br/>7 virtual devices"]
Metrics["Prometheus Exporter<br/>/metrics"]
end
subgraph "Observability Stack"
Prom["Prometheus"]
Graf["Grafana"]
end
Claude <-->|MCP Protocol| Server
Server --> Resources
Server --> Tools
Server --> Prompts
Resources --> Sim
Tools --> Sim
Sim --> Metrics
Metrics --> Prom
Prom --> Graf
style Claude fill:#6B48FF,color:#fff
style Server fill:#0EA5E9,color:#fff
style Sim fill:#10B981,color:#fff
style Graf fill:#F59E0B,color:#fffData Flow
Network Simulator generates realistic, time-varying metrics for 7 virtual devices
MCP Resources expose read-only telemetry data (device status, interfaces, latency, bandwidth, topology, alerts)
MCP Tools provide executable diagnostics (ping, traceroute, interface check, config viewer, baseline comparison, interface restart)
MCP Prompts offer guided workflows (health briefing, troubleshooting, capacity planning)
Prometheus + Grafana provide visual dashboards alongside the AI interface
Related MCP server: LogicMonitor MCP Server
Quick Start
1. Clone the repository
git clone https://github.com/yourusername/netpulse.git
cd netpulse2. Launch the full stack
docker compose up -dThis starts:
NetPulse MCP Server on port
8080(SSE transport)Prometheus on port
9091Grafana on port
3000(login:admin/netpulse)
3. Connect Claude Desktop
Add to your Claude Desktop MCP configuration (claude_desktop_config.json):
{
"mcpServers": {
"netpulse": {
"command": "python",
"args": ["-m", "netpulse.server"],
"cwd": "/path/to/netpulse"
}
}
}Or for SSE transport:
{
"mcpServers": {
"netpulse": {
"url": "http://localhost:8080/sse"
}
}
}Now ask Claude: "Give me a network health summary" β and watch it query real telemetry!
MCP Interface Reference
Resources (Read-Only Data)
URI | Description |
| Status of all 7 monitored devices with CPU, memory, temperature |
| Interface metrics for a specific device |
| Latency matrix between all connected endpoints |
| Top 10 bandwidth consumers |
| Network topology as nodes + edges with health status |
| Currently firing alerts with severity |
Tools (Executable Actions)
Tool | Description | Key Parameters |
| Ping a device and get RTT stats |
|
| Trace network path to destination |
|
| Detailed interface diagnostics |
|
| View device running configuration |
|
| Compare current vs historical baseline |
|
| Bounce an interface (requires confirmation) |
|
Prompts (Workflow Templates)
Prompt | Description | Arguments |
| NOC morning briefing workflow | None |
| Guided connectivity diagnosis |
|
| Bandwidth analysis and projections | None |
Configuration
Environment Variables
Variable | Default | Description |
|
| Server bind address |
|
| MCP server port |
|
| Transport mode ( |
|
| Logging level |
|
| Metric polling interval (seconds) |
Device Inventory
Edit src/netpulse/config/devices.yaml to customize the simulated network topology. The default includes 7 devices across 2 data centers and a branch office.
Thresholds
Edit src/netpulse/config/thresholds.yaml to adjust alerting thresholds for CPU, memory, latency, packet loss, bandwidth, and temperature.
Fault Injection (Demo)
Inject faults to demonstrate AI-driven incident detection:
# Take down the WAN link
python -m netpulse.simulators.fault_injector --scenario link_down
# Spike CPU on the core router
python -m netpulse.simulators.fault_injector --scenario cpu_spike
# Simulate interface flapping
python -m netpulse.simulators.fault_injector --scenario interface_flap
# Take down a device
python -m netpulse.simulators.fault_injector --scenario device_down
# Saturate bandwidth
python -m netpulse.simulators.fault_injector --scenario bandwidth_saturationThen ask Claude: "Are there any network issues right now?"
Development
Local Setup
# Create virtual environment
python -m venv .venv
source .venv/bin/activate # or .venv\Scripts\activate on Windows
# Install with dev dependencies
pip install -e ".[dev]"
# Run the server locally (stdio mode)
python -m netpulse.serverRunning Tests
pytest --cov=netpulse --cov-report=term-missingCode Quality
# Linting
ruff check src/ tests/
# Type checking
mypy src/netpulse/Simulated Network Topology
βββββββββββββββ βββββββββββββββ
β core-rtr-01 βββββββββββΊβ core-rtr-02 β
β 10.0.0.1 β 10Gbps β 10.0.0.2 β
β Data Ctr A βbackbone β Data Ctr B β
ββββ¬βββββββ¬βββββ ββββββββ¬ββββββββ
β β β
10G β β 100M 10G β
β β β
βββββββββ΄βββ β βββββββββ΄βββ
βdist-sw-01β β βdist-sw-02β
β 10.0.1.1 β β β 10.0.1.2 β
βββββββ¬βββββ β ββββββββββββ
β β
1G β β
β β
βββββββ΄βββββ β βββββββββββββ
βedge-fw-01β ββββββββββΊβ wan-rtr-01 β
β 10.0.2.1 β WAN β 10.0.4.1 β
ββββββββββββ ββββββββ¬ββββββ
β 1G
ββββββββ΄βββββββ
βaccess-sw-01 β
β 10.0.3.1 β
β Branch Off 1β
βββββββββββββββAuthor
Hind Boukhairat β IoT dev specializing in network monitoring and AIOps, transitioning into AI Integration Engineering. Holder of two MCP certifications from Anthropic/Skilljar (Introduction + Advanced Topics).
NetPulse is part of a portfolio showcasing the intersection of telecom/network operations and AI orchestration.
License
MIT β see LICENSE for details.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/hind77/Netpulse'
If you have feedback or need assistance with the MCP directory API, please join our Discord server