by jamesbrink
Coroot offers a robust data observability platform with Prometheus process monitoring, software network monitoring, and
Connects to Coroot observability platform to monitor applications, analyze logs and traces, and troubleshoot infrastructure issues. Provides comprehensive application performance monitoring through Coroot's API.
Coroot is a community-built MCP server published by jamesbrink that provides AI assistants with tools and capabilities via the Model Context Protocol. Coroot offers a robust data observability platform with Prometheus process monitoring, software network monitoring, and It is categorized under developer tools, productivity.
You can install Coroot in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
MIT
Coroot is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Add new capabilities to Claude beyond text generation
Example
Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Automate multi-step workflows combining AI and external tools
Example
Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Share your MCP server with the developer community
According to our notes, Coroot benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
Coroot has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
Coroot reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
I recommend Coroot for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
Coroot is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
Useful MCP listing: Coroot is the kind of server we cite when onboarding engineers to host + tool permissions.
Coroot is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
We wired Coroot into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
We wired Coroot into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
Coroot reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
showing 1-10 of 69
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.
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"
}
}
}
}
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.
# Install and run directly
uvx mcp-coroot
pip install mcp-coroot
docker run --rm -i \
-e COROOT_BASE_URL="http://localhost:8080" \
-e COROOT_USERNAME="admin" \
-e COROOT_PASSWORD="your-password" \
jamesbrink/mcp-coroot:latest
git clone https://github.com/jamesbrink/mcp-coroot.git
cd mcp-coroot
uv sync --all-groups
uv run mcp-coroot
Best for users with basic authentication. The server automatically handles login and session management.
Required for organizations using:
To get your session cookie:
auth cookieOnly supports data ingestion endpoints (/v1/*). Cannot be used for management APIs.
The server provides 61 tools organized into functional categories:
get_current_user - Get authenticated user informationupdate_current_user - Update user profilelist_users - List all userscreate_user - Create new usersget_roles - View roles and permissionslist_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 keysget_application - Comprehensive application metricsget_application_logs - Search and analyze logsget_application_traces - View distributed tracesget_applications_overview - All applications summaryget_nodes_overview - Infrastructure overviewget_traces_overview - Tracing summaryget_deployments_overview - Deployment historyget_risks_overview - Risk assessmentlist_dashboards - View dashboardscreate_dashboard - Create dashboardget_dashboard - Get dashboard detailsupdate_dashboard - Update dashboarddelete_dashboard - Remove dashboardlist_integrations - View integrationsconfigure_integration - Configure integrationtest_integration - Test connectivitydelete_integration - Remove integrationlist_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 appsIncluding RCA, profiling, cloud pricing, database instrumentation, SSO/AI configuration, and more.
"Show me all applications in the production project"
"Check the health status of the API service"
"Are there any critical incidents right now?"
"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"
"Set up Slack notifications for critical alerts"
"Create a dashboard for monitoring Redis performance"
"Configure SLO thresholds for the API service"
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.
# Run all tests
uv run pytest
# Run with coverage
uv run pytest --cov
# Run specific tests
uv run pytest tests/test_server.py -v
# Type checking
uv run mypy src
# Linting
uv run ruff check src tests
# Formatting
uv run ruff format src tests
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.
Some endpoints return large datasets. Use time filters:
get_application_traces - Use from_timestamp and to_timestampget_application_profiling - Limit time range to reduce data sizeContributions are welcome! Please:
MIT License - see LICENSE file for details.
Prerequisites
Time Estimate
15-60 minutes depending on server complexity
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ Use when
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid when
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.