Add MCP documentation (#20469)
Co-authored-by: ilyam8 <ilya@netdata.cloud>
Kanela committed
Jun 13, 2025 at 11:16 UTC
1a959882689dc231afb0e7a34a59713b30e49c8f
1 file changed
+133
docs/learn/mcp.md
new
+133
@@ -0,0 +1,133 @@
1
+# Netdata MCP Integration: AI-Powered Infrastructure Analysis
2
+
3
+## What is MCP?
4
+
5
+**Model Context Protocol (MCP)** is a new open standard that allows AI assistants to connect directly to your data sources and tools. Think of it as a bridge that lets AI systems access and analyze your real-time infrastructure data instead of just providing generic advice.
6
+
7
+:::note
8
+
9
+**Learn More**: MCP is an open standard created by Anthropic. For technical details about the protocol specification, visit [Anthropic's MCP documentation](https://modelcontextprotocol.io/).
10
+
11
+:::
12
+
13
+## How Netdata is Pioneering AI-Powered Monitoring
14
+
15
+Netdata is the **first monitoring platform** to integrate MCP, making us pioneers in AI-powered infrastructure analysis. We've built a direct connection between advanced AI models (like Claude) and your Netdata monitoring data, creating an intelligent troubleshooting partner that understands your specific infrastructure.
16
+
17
+### What Makes This Revolutionary
18
+
19
+**Traditional monitoring**: You look at charts and graphs, manually correlating data across different services to find problems.
20
+
21
+**Netdata with MCP**: AI analyzes your actual monitoring data in real-time, automatically correlates anomalies across your entire infrastructure, and provides expert-level post-mortem analysis.
22
+
23
+## What This Changes for You
24
+
25
+### Instant Expert Analysis
26
+
27
+Instead of spending hours analyzing charts during an incident, you can now:
28
+
29
+- **Ask natural questions**: "What caused the outage between 13:00-13:30 UTC?"
30
+- **Get comprehensive post-mortems**: AI analyzes your metrics, identifies root causes, and maps dependency chains
31
+- **Understand complex correlations**: AI detects which services were affected and why
32
+
33
+### Real-World Example
34
+
35
+**The Problem**: EMQX message broker goes down, affecting multiple services across your infrastructure.
36
+
37
+```mermaid
38
+flowchart TD
39
+ A("🚨 EMQX Outage Occurs")
40
+
41
+ B("📊 Traditional Approach")
42
+ C("🤖 Netdata + MCP")
43
+
44
+ D("Manual dashboard review<br/>⏱️ Hours of analysis")
45
+ E("AI analyzes all metrics<br/>⚡ Instant correlation")
46
+
47
+ F("❌ Slow resolution<br/>Missed dependencies")
48
+ G("✅ Fast resolution<br/>Complete root cause")
49
+
50
+ A --> B
51
+ A --> C
52
+ B --> D
53
+ C --> E
54
+ D --> F
55
+ E --> G
56
+
57
+ %% Styling
58
+ classDef problem fill:#ffeb3b,stroke:#333,stroke-width:2px
59
+ classDef traditional fill:#ff7043,stroke:#333,stroke-width:2px
60
+ classDef ai fill:#42a5f5,stroke:#333,stroke-width:2px
61
+ classDef outcome fill:#f5f5f5,stroke:#333,stroke-width:2px
62
+
63
+ class A problem
64
+ class B,D traditional
65
+ class C,E ai
66
+ class F,G outcome
67
+```
68
+
69
+### Advanced Anomaly Detection
70
+
71
+Your AI assistant can:
72
+
73
+- **Detect anomaly patterns** across your entire infrastructure
74
+- **Identify cascade failures** before they become critical
75
+- **Explain complex service dependencies** in plain language
76
+- **Predict which services will be affected** by specific component failures
77
+
78
+## Current Capabilities
79
+
80
+### What You Can Do Today
81
+
82
+| Capability | What You Get | Key Benefits |
83
+|-----------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------|
84
+| **Infrastructure Analysis** | **Post-mortem analysis** of incidents with **root cause identification**, **real-time anomaly correlation** across all your services, **service dependency mapping** and impact analysis, **performance bottleneck identification** | Understand complex incidents in minutes instead of hours, identify cascading failures before they spread |
85
+| **Intelligent Querying** | Ask questions about your infrastructure in **natural language**, get **explanations of complex metrics** and their relationships, understand **streaming configurations** and network topologies, analyze **resource usage patterns** and trends | No more manual chart correlation - just ask and get expert-level insights |
86
+| **Expert Troubleshooting** | **AI-powered investigation** of performance issues, **automated correlation** of events across your infrastructure, **context-aware recommendations** based on your specific setup | Get the analysis that would normally require a senior engineer, available 24/7 |
87
+
88
+### How to Get Started
89
+
90
+1. **Install Netdata nightly build** (required for MCP support)
91
+2. **Set up the MCP bridge** using our nd-mcp tool
92
+3. **Connect your AI assistant** (Claude Desktop recommended)
93
+4. **Start asking questions** about your infrastructure
94
+
95
+:::note
96
+
97
+**Current Version**: MCP integration works with both individual Netdata agents and parent agents that aggregate data from multiple nodes. When connected to a parent, AI can analyze data across all nodes that stream to that parent.
98
+
99
+:::
100
+
101
+## What's Coming Next
102
+
103
+### Netdata Cloud Integration
104
+
105
+**The next major step**: MCP will integrate directly with Netdata Cloud, giving you access to your complete infrastructure data:
106
+
107
+- **Organization-wide analysis** across all your monitored infrastructure
108
+- **Cross-room correlation** for complex distributed systems
109
+- **Complete infrastructure visibility** through AI analysis
110
+- **Team-wide insights** from your centralized monitoring data
111
+
112
+### Beyond Single Nodes
113
+
114
+**Current capability**: MCP integration works with individual Netdata agents and parent agents that aggregate multiple nodes.
115
+
116
+**Coming soon**: Direct access to your Netdata Cloud data, enabling AI analysis across your entire infrastructure ecosystem with full organizational context.
117
+
118
+## The Future of Infrastructure Monitoring
119
+
120
+With Netdata MCP, we're moving toward a future where:
121
+
122
+- **AI understands your infrastructure** as well as your best engineers
123
+- **Troubleshooting becomes conversational** rather than manual chart analysis
124
+- **Post-mortems write themselves** with complete root cause analysis
125
+- **Your monitoring system becomes a team member** that helps solve problems
126
+
127
+**Join us in pioneering the next generation of intelligent infrastructure monitoring.**
128
+
129
+:::tip
130
+
131
+**Ready to try it?** Contact us to get early access to MCP integration, or check our GitHub repository for the latest nd-mcp tools and setup instructions.
132
+
133
+:::
\ No newline at end of file