MCP Server for Coroot
A Model Context Protocol (MCP) server that provides seamless integration with Coroot observability platform. This server enables MCP clients to monitor applications, analyze performance metrics, examine logs and traces, and manage infrastructure through Coroot's comprehensive API.
Getting Started
Add this configuration to your MCP client settings:
{
"mcpServers": {
"coroot": {
"command": "uvx",
"args": ["mcp-coroot"],
"env": {
"COROOT_BASE_URL": "http://localhost:8080",
"COROOT_USERNAME": "admin",
"COROOT_PASSWORD": "your-password"
}
}
}
}
Using Docker:
{
"mcpServers": {
"coroot": {
"command": "docker",
"args": ["run", "--rm", "-i",
"-e", "COROOT_BASE_URL=http://localhost:8080",
"-e", "COROOT_USERNAME=admin",
"-e", "COROOT_PASSWORD=your-password",
"jamesbrink/mcp-coroot:latest"]
}
}
}
For SSO/MFA users, use session cookie authentication instead:
{
"mcpServers": {
"coroot": {
"command": "uvx",
"args": ["mcp-coroot"],
"env": {
"COROOT_BASE_URL": "http://localhost:8080",
"COROOT_SESSION_COOKIE": "your-auth-cookie-value"
}
}
}
}
Environment Variables
COROOT_BASE_URL- Your Coroot instance URL (required)COROOT_USERNAME- Username for basic authenticationCOROOT_PASSWORD- Password for basic authenticationCOROOT_SESSION_COOKIE- Session cookie for SSO/MFA usersCOROOT_API_KEY- API key (limited to data ingestion only)
That's it! Your MCP client can now interact with your Coroot instance.
Features
Core Capabilities
- Application Monitoring - Real-time metrics, health checks, and performance analysis
- Log Analysis - Search, filter, and analyze application logs with pattern detection
- Distributed Tracing - Trace requests across microservices and identify bottlenecks
- Infrastructure Overview - Monitor nodes, containers, and system resources
- Incident Management - Track and analyze incidents with root cause analysis
- Performance Profiling - CPU and memory profiling with flame graphs
Management Features
- Project Management - Create, configure, and manage Coroot projects
- Integration Configuration - Set up Prometheus, Slack, PagerDuty, and more
- Dashboard Customization - Create and manage custom dashboards
- Cost Tracking - Monitor cloud costs with custom pricing rules
- User & Access Control - Manage users, roles, and permissions
Advanced Features
- AI-Powered RCA - Automatic root cause analysis for application issues
- Risk Assessment - Identify and track infrastructure and application risks
- Deployment Tracking - Monitor deployments and their impact
- SLO Management - Configure and track Service Level Objectives
- Database Instrumentation - Specialized monitoring for databases
Installation
Using uvx (Recommended)
# Install and run directly
uvx mcp-coroot
Using pip
pip install mcp-coroot
Using Docker
docker run --rm -i \
-e COROOT_BASE_URL="http://localhost:8080" \
-e COROOT_USERNAME="admin" \
-e COROOT_PASSWORD="your-password" \
jamesbrink/mcp-coroot:latest
From Source
git clone https://github.com/jamesbrink/mcp-coroot.git
cd mcp-coroot
uv sync --all-groups
uv run mcp-coroot
Authentication Methods
Username/Password
Best for users with basic authentication. The server automatically handles login and session management.
Session Cookie (SSO/MFA)
Required for organizations using:
- Single Sign-On (SAML, OIDC)
- Multi-Factor Authentication (2FA/MFA)
- Advanced authentication workflows
To get your session cookie:
- Login to Coroot through your browser
- Open Developer Tools (F12)
- Go to Application/Storage → Cookies
- Copy the value of the
authcookie
API Key
Only supports data ingestion endpoints (/v1/*). Cannot be used for management APIs.
Available Tools
The server provides 61 tools organized into functional categories:
🔐 Authentication & Users (5 tools)
get_current_user- Get authenticated user informationupdate_current_user- Update user profilelist_users- List all userscreate_user- Create new usersget_roles- View roles and permissions
📊 Project Management (9 tools)
list_projects- List all accessible projectsget_project- Get project detailscreate_project- Create new projectget_project_status- Check project healthupdate_project_settings- Update project configurationdelete_project- Delete projectlist_api_keys- View API keyscreate_api_key- Generate API keysdelete_api_key- Delete API keys
🚀 Application Monitoring (3 tools)
get_application- Comprehensive application metricsget_application_logs- Search and analyze logsget_application_traces- View distributed traces
🌐 Overview & Analysis (5 tools)
get_applications_overview- All applications summaryget_nodes_overview- Infrastructure overviewget_traces_overview- Tracing summaryget_deployments_overview- Deployment historyget_risks_overview- Risk assessment
📈 Dashboard Management (5 tools)
list_dashboards- View dashboardscreate_dashboard- Create dashboardget_dashboard- Get dashboard detailsupdate_dashboard- Update dashboarddelete_dashboard- Remove dashboard
🔌 Integrations (4 tools)
list_integrations- View integrationsconfigure_integration- Configure integrationtest_integration- Test connectivitydelete_integration- Remove integration
⚙️ Configuration (9 tools)
list_inspections- View inspection typesget_inspection_config- Get inspection settingsupdate_inspection_config- Update inspectionsget_application_categories- View categoriescreate_application_category- Create new categoryupdate_application_category- Update existing categorydelete_application_category- Delete categoryget_custom_applications- View custom appsupdate_custom_applications- Define custom apps
🔍 Advanced Features (15 tools)
Including RCA, profiling, cloud pricing, database instrumentation, SSO/AI configuration, and more.
Example Usage
Basic Monitoring
"Show me all applications in the production project"
"Check the health status of the API service"
"Are there any critical incidents right now?"
Troubleshooting
"Search for error logs in the payment service from the last hour"
"Show me slow database queries"
"Analyze the root cause of high latency in the frontend"
Configuration
"Set up Slack notifications for critical alerts"
"Create a dashboard for monitoring Redis performance"
"Configure SLO thresholds for the API service"
Development
Using Test PyPI Version
To use the pre-release version from Test PyPI:
{
"mcpServers": {
"coroot": {
"command": "uvx",
"args": [
"--index-url",
"https://test.pypi.org/simple/",
"--extra-index-url",
"https://pypi.org/simple/",
"mcp-coroot"
],
"env": {
"COROOT_BASE_URL": "http://localhost:8080",
"COROOT_USERNAME": "admin",
"COROOT_PASSWORD": "your-password"
}
}
}
}
Note: The --extra-index-url is required because Test PyPI doesn't host all dependencies.
Testing
# Run all tests
uv run pytest
# Run with coverage
uv run pytest --cov
# Run specific tests
uv run pytest tests/test_server.py -v
Code Quality
# Type checking
uv run mypy src
# Linting
uv run ruff check src tests
# Formatting
uv run ruff format src tests
API Compatibility
This MCP server is compatible with Coroot v1.0+ and implements the full management API surface. For data ingestion endpoints, use the Coroot API directly with your API key.
Troubleshooting
Connection Issues
- Verify Coroot is accessible at the configured URL
- Check firewall rules and network connectivity
- Ensure credentials are correct
Authentication Errors
- Username/password authentication is recommended for automatic login
- Session cookies expire after 7 days of inactivity
- API keys only work for data ingestion, not management APIs
Large Response Errors
Some endpoints return large datasets. Use time filters:
get_application_traces- Usefrom_timestampandto_timestampget_application_profiling- Limit time range to reduce data size
Contributing
Contributions are welcome! Please:
- Fork the repository
- Create a feature branch
- Add tests for new functionality
- Ensure all tests pass
- Submit a pull request
License
MIT License - see LICENSE file for details.