octomind mcp server: let agents create and manage e2e tests
Octomind provides a whole e2e platform for test creation, execution and management including auto-fix. With this MCP server you can use Octomind tools and resources in your local development environment and enable it to create new e2e tests, execute them and more. see https://octomind.dev/ and https://octomind.dev/docs/mcp/install-octomind-mcp for more details.
See it in action together with testrail mcp
Configuration
Environment Variables
The server uses the following environment variables:
APIKEY- The API key for Octomind API (required)OCTOMIND_API_URL- Base URL for the API endpoint to use (defaults to https://app.octomind.dev/api)REDIS_URL- Redis connection URL for session storage (optional, format: redis://host:port)SESSION_EXPIRATION_SECONDS- Time in seconds after which sessions expire (optional, Redis only)
Command Line Options
The server supports the following command line options:
-s, --sse- Enable SSE transport mode-t, --stream- Enable Streamable HTTP transport mode-c, --clients- Show client configuration examples-p, --port <port>- Port to listen on (default: 3000)-r, --redis-url <url>- Redis URL for session storage-e, --session-expiration <seconds>- Session expiration time in seconds
Session Storage
The server supports two types of session storage:
- In-memory storage (default) - Sessions are stored in memory and will be lost when the server restarts
- Redis storage - Sessions are stored in Redis and can persist across server restarts
For production deployments, it's recommended to use Redis storage with an appropriate session expiration time. The Redis storage option also enables horizontal scaling with multiple server instances.
Logging Configuration
LOG_FILENAME- The file to write logs to (only for debugging). If not set, logging is disabledLOG_LEVEL- The log level to use (defaults to info)
Tools
The following tools are implemented in this MCP server:
search- Search the Octomind documentation for a given querygetTestCase- Retrieve a test case for a given test target and test case IDexecuteTests- Trigger test execution for a given test target on a specified URLgetEnvironments- List environments for a test targetcreateEnvironment- Create a new environment for a test targetupdateEnvironment- Update an existing environmentdeleteEnvironment- Delete an environmentgetTestReports- Retrieve test reports for a test targetgetTestReport- Get a specific test report by IDdiscovery- Create a test case with a description or promptgetPrivateLocations- List all private locations configured for the organizationgetVersion- Get the current version of the Octomind MCP server
Installation
You can get configuration snippets for different clients by running:
npx @octomind/octomind-mcp --clients
This will output configuration examples for Claude Desktop, Cursor, and Windsurf. Here are the configuration files for most clients:
Installing via Smithery
To install octomind-mcp for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @OctoMind-dev/octomind-mcp --client claude
Claude Desktop (.claude-config.json)
{
"mcpServers": {
"octomind-mcp": {
"name": "Octomind MCP Server",
"command": "npx",
"args": [
"-y",
"@octomind/octomind-mcp@latest"
],
"env": {
"APIKEY": "your-api-key-here"
}
}
}
}
Cursor (cursor.json)
{
"mcpServers": {
"octomind-mcp": {
"name": "Octomind MCP Server",
"command": "npx",
"args": [
"-y",
"@octomind/octomind-mcp@latest"
],
"env": {
"APIKEY": "your-api-key-here"
}
}
}
}
Windsurf (mcp_config.json)
{
"mcpServers": {
"octomind-mcp": {
"name": "Octomind MCP Server",
"command": "npx",
"args": [
"-y",
"@octomind/octomind-mcp@latest"
],
"environment": {
"APIKEY": "your-api-key-here"
}
}
}
}
Note: Replace your-api-key-here with your actual API key.
To get an APIKEY see here https://octomind.dev/docs/get-started/execution-without-ci#create-an-api-key
Listings / Integrations
Certified by MCPHub
Recommend MCP Servers 💡
mcp-system-health
Provides real-time health and performance metrics for remote Linux servers via SSH, integrating with AI assistants like Claude through the MCP protocol.
@hiyorineko/mcp-rollbar-server
A dynamic MCP server implementation for Rollbar API integration, enabling LLMs to interact with Rollbar error tracking data.
trello-report-mcp
MCP server for generating detailed Trello board reports by quarter or year
climatiq-mcp-server
A Model Context Protocol (MCP) server for accessing the Climatiq API to calculate carbon emissions. This allows AI assistants to perform real-time carbon calculations and provide climate impact insights.
aaomidi/mcp-bazel
An MCP server that exposes Bazel tools for build, test, and dependency analysis.
Ixe1/code-scanner-server
A CLI tool and MCP server that scans code files for definitions and provides LLM-friendly output

