FusionReactor MCP Server
Provides tools to list and get alert rules and alerts via Grafana Alerting API, enabling AI assistants to monitor and manage alerts from FusionReactor Cloud.
Provides tools to query metrics, metric series, and labels via Prometheus-compatible API, enabling AI assistants to retrieve and analyze metrics from FusionReactor Cloud.
Click on "Deploy 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., "@FusionReactor MCP Serverwhat are the active alerts right now?"
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.
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 |
| Prometheus / Mimir API |
Logs |
| Loki API |
Alerts |
| Grafana Alerting API |
Related MCP server: Monti APM MCP Server
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 startEnvironment Variables
Variable | Required | Description |
| Yes | Your FusionReactor API key |
| No | API base URL. Defaults to |
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 buildProject 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 clientAPI 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}/valuesLogs —
/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/seriesAlerts —
/g/api/ruler/grafana/api/v1/rules,/g/api/alertmanager/grafana/api/v2/alerts,/g/api/alertmanager/grafana/api/v2/alerts/groups
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Let AI agents query data and act across all your business apps via MCP.
Query application logs, traces, and metrics from your AI coding assistant via Foam's MCP server.
Access New Relic observability data through MCP - query metrics, logs, traces, entities, and more
Unified MCP Server is a remote MCP connector for AI agents and vertical AI products that provides access to 22,000+ authorized SaaS tools across 400+ integrations and 24 categories directly inside LLMs (Claude, GPT, Gemini, Cohere). Tools operate only on explicitly authorized customer connections, enabling agents to safely read and write against live third-party systems.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to interact with JasperReports Server for report execution, resource management, and job scheduling via MCP tools.9 npm9GPL 3.0
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to interact with Monti APM for Meteor application performance monitoring.33 npm5MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to query AWS CloudWatch metrics, alarms, and logs read-only via MCP, providing rapid health snapshots and triage without console navigation.1MIT
- AlicenseAqualityDmaintenanceMCP server enabling AI assistants to interact with your LogicMonitor, providing 125 tools for comprehensive monitoring and management operations.7087 npm13AGPL 3.0