FusionReactor MCP Server
Enables AI assistants to query FusionReactor Cloud metrics, logs, and alerts via MCP tools.
README
FusionReactor MCP Server
A TypeScript Model Context Protocol (MCP) server that exposes FusionReactor Cloud monitoring data — metrics, logs, and alerts — as callable tools for AI assistants.
Features
| Category | Tools | Backend |
|---|---|---|
| Metrics | query_metrics, query_metrics_range, list_metric_series, list_metric_label_names, list_metric_label_values |
Prometheus / Mimir API |
| Logs | query_logs, query_logs_range, list_log_label_names, list_log_label_values, list_log_series |
Loki API |
| Alerts | list_alert_rules, list_alert_rules_by_namespace, get_alerts, get_alert_groups |
Grafana Alerting API |
Prerequisites
- Node.js ≥ 18
- A FusionReactor Cloud account with an API key
Quick Start
# 1. Install dependencies
npm install
# 2. Build
npm run build
# 3. Run (requires API key)
FUSIONREACTOR_API_KEY=your-key-here npm start
Environment Variables
| Variable | Required | Description |
|---|---|---|
FUSIONREACTOR_API_KEY |
Yes | Your FusionReactor API key |
FUSIONREACTOR_API_URL |
No | API base URL. Defaults to https://api.fusionreactor.io |
Using with an MCP Client
Add this server to your MCP client configuration. For example, in Claude Desktop or VS Code:
{
"mcpServers": {
"fusionreactor": {
"command": "node",
"args": ["<path-to-project>/dist/index.js"],
"env": {
"FUSIONREACTOR_API_KEY": "your-key-here"
}
}
}
}
Development
# Watch mode — recompiles on file changes
npm run dev
# One-time build
npm run build
Project Structure
src/
├── index.ts # Entry point — bootstraps MCP server with stdio transport
├── client.ts # FusionReactor HTTP API client (metrics, logs, alerts)
└── tools.ts # MCP tool definitions wired to the API client
API Endpoints Used
The server communicates with FusionReactor Cloud's Grafana-compatible API:
- Metrics —
/g/api/v1/query,/g/api/v1/query_range,/g/api/v1/series,/g/api/v1/labels,/g/api/v1/label/{name}/values - Logs —
/g/loki/api/v1/query,/g/loki/api/v1/query_range,/g/loki/api/v1/labels,/g/loki/api/v1/label/{name}/values,/g/loki/api/v1/series - Alerts —
/g/api/ruler/grafana/api/v1/rules,/g/api/alertmanager/grafana/api/v2/alerts,/g/api/alertmanager/grafana/api/v2/alerts/groups
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.