ReportPortal
MCP server for ReportPortal
What is ReportPortal?
ReportPortal is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server for reportportal
MCP server for ReportPortal
This server falls under the Monitoring & Observability category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MCP server for ReportPortal
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx reportportalConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use ReportPortal
ReportPortal MCP Server is a Go-based bridge that connects AI assistants such as Claude Desktop, GitHub Copilot, and Cursor directly to a ReportPortal test reporting instance. It lets QA testers and managers query test launches, retrieve failure details, trigger quality gate analysis, and manage test cases through plain English rather than navigating the ReportPortal UI. Starting from version 2.x it also integrates with the ReportPortal Test Case Management System, supporting test cases, folders, milestones, and test plans.
Prerequisites
- A running ReportPortal instance (self-hosted or cloud) with version 26.1+ for TMS features
- A ReportPortal API token (generated from your user Profile page)
- Docker installed (recommended installation method) OR a pre-built binary downloaded from GitHub Releases
- Claude Desktop, Cursor, VS Code Copilot, or another MCP-compatible client
Gather your ReportPortal credentials
You need three values: your ReportPortal host URL (e.g. https://reportportal.example.com), your project key (found at Settings → General, not the display name), and an API token from your Profile page. Never commit these to version control.
Pull the Docker image
The official Docker image is the recommended way to run the server locally. Pull it from DockerHub.
docker pull reportportal/mcp-serverAdd the server to your MCP client configuration
Open your claude_desktop_config.json (or equivalent for your MCP client) and add the reportportal entry. The env block injects your credentials securely without hard-coding them in args.
{
"mcpServers": {
"reportportal": {
"command": "docker",
"args": [
"run", "-i", "--rm",
"-e", "RP_API_TOKEN",
"-e", "RP_HOST",
"-e", "RP_PROJECT",
"reportportal/mcp-server"
],
"env": {
"RP_API_TOKEN": "your-api-token",
"RP_HOST": "https://your-reportportal-instance.com",
"RP_PROJECT": "your_project_key"
}
}
}
}Restart your MCP client
Fully quit and reopen Claude Desktop (or your chosen MCP client) so the configuration is loaded. The reportportal server should appear in your connected servers list.
Test the connection with a simple query
Ask your AI assistant to list recent test launches. If it returns data from your ReportPortal instance, the integration is working correctly.
ReportPortal Examples
Client configuration
Full Docker-based claude_desktop_config.json entry for ReportPortal MCP Server.
{
"mcpServers": {
"reportportal": {
"command": "docker",
"args": [
"run", "-i", "--rm",
"-e", "RP_API_TOKEN",
"-e", "RP_HOST",
"-e", "RP_PROJECT",
"reportportal/mcp-server"
],
"env": {
"RP_API_TOKEN": "your-api-token",
"RP_HOST": "https://your-reportportal-instance.com",
"RP_PROJECT": "your_project_key"
}
}
}
}Prompts to try
Natural language queries that map to the built-in tools exposed by the server.
- "List the 5 most recent test launches"
- "What tests failed in the latest run?"
- "Run quality gate analysis on launch 12345"
- "Show me details of launch with ID 119000"
- "Run auto analysis on launch 'Regression Suite'"
- "List test cases in the Smoke folder"
- "Create a test plan for the Q2 sprint milestone"Troubleshooting ReportPortal
Docker container exits immediately with no output
Ensure you include the '-i' flag in the docker args so stdin stays open for MCP JSON-RPC. Without it, the container receives no input and exits. Also verify that RP_HOST, RP_API_TOKEN, and RP_PROJECT are correctly set in the env block.
API returns 401 Unauthorized for all requests
The RP_API_TOKEN must be a ReportPortal API key, not a regular password. Generate one from your ReportPortal Profile page under the API Keys section. Tokens are scoped to the user who created them.
TMS tools (Create Test Case, List Milestones, etc.) return 'not found' errors
TMS features require ReportPortal version 26.1 or later with the TMS module enabled. Check your ReportPortal instance version and confirm TMS is activated in the admin settings.
Frequently Asked Questions about ReportPortal
What is ReportPortal?
ReportPortal is a Model Context Protocol (MCP) server that mcp server for reportportal It connects AI assistants to external tools and data sources through a standardized interface.
How do I install ReportPortal?
Follow the installation instructions on the ReportPortal GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with ReportPortal?
ReportPortal works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is ReportPortal free to use?
Yes, ReportPortal is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
ReportPortal Alternatives — Similar Monitoring & Observability Servers
Looking for alternatives to ReportPortal? Here are other popular monitoring & observability servers you can use with Claude, Cursor, and VS Code.
Netdata
★ 78.9kReal-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Kubeshark
★ 11.9keBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS without keys. Queryable by AI agents via MCP and humans via dashboard.
Mission Control
★ 4.9kSelf-hosted AI agent orchestration platform: dispatch tasks, run multi-agent workflows, monitor spend, and govern operations from one mission control dashboard.
Grafana
★ 3.0kThis MCP server enables natural-language querying of Grafana logs by automatically detecting log sources and service labels. It provides read-only access to log data with intelligent caching for efficient repeat queries.
Sentrux
★ 2.4kReal-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.
OpenInference
★ 986OpenTelemetry Instrumentation for AI Observability
Browse More Monitoring & Observability MCP Servers
Explore all monitoring & observability servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up ReportPortal in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use ReportPortal?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.