Currents MCP Server

How to use

You use Currents MCP by running it as a local MCP server or by pointing your MCP client to Currents through the provided command. This server exposes actions that let your AI tools fetch projects, examine test runs, retrieve performance metrics, and manage runs or webhooks within Currents. Ensure you have a valid Currents API key to authorize these requests, and configure your MCP client to load Currents as an MCP source.

How to install

Prerequisites: you need Node.js and npm (or a compatible runtime that supports NPX). Install Node.js from the official sources if you do not already have it.

1. Obtain your Currents API key from your Currents account setup. You will use this key to authorize MCP requests.

2. Add Currents MCP to your MCP client configuration. Use the following snippet to enable Currents in your MCP client and point it to the Currents MCP package.

{
  "mcpServers": {
    "currents": {
      "command": "npx",
      "args": ["-y", "@currents/mcp"],
      "env": {
        "CURRENTS_API_KEY": "your-api-key"
      }
    }
  }
}

Claude integration and desktop setup

To connect Currents MCP to Claude, run the following command to register Currents as an MCP transport for Claude Code.

claude mcp add --transport stdio currents --env CURRENTS_API_KEY=<KEY> -- npx -y @currents/mcp

To enable Currents MCP on Claude Desktop, add the following to your claude_desktop_config.json file.

{
  "mcpServers": {
    "currents": {
      "command": "npx",
      "args": ["-y", "@currents/mcp"],
      "env": {
        "CURRENTS_API_KEY": "your-api-key"
      }
    }
  }
}

currents-get-projects

Retrieves the list of projects available in Currents for selection and context.

currents-get-project

Fetches a single Currents project by its ID to inspect details and metrics.

currents-get-project-insights

Retrieves aggregated run and test metrics for a project within a specified date range.

currents-get-runs

Returns a list of runs for a given project, with optional filtering by status, date, or other criteria.

currents-get-run-details

Provides detailed information for a specific test run, including status and results.

currents-find-run

Searches for a run using query parameters to locate a matching execution.

currents-cancel-run

Cancels a run that is currently in progress.

currents-reset-run

Resets failed spec files within a run to allow re-execution.

currents-delete-run

Deletes a run and all data associated with it.

currents-cancel-run-github-ci

Cancels a run based on a GitHub Actions workflow run ID and attempt number.

currents-get-spec-instance

Retrieves debugging data for a specific execution of a test spec file by instanceId.

currents-get-spec-files-performance

Retrieves performance metrics for spec files within a project over a date range.

currents-get-tests-performance

Gets aggregated test metrics for a project across a date range.

currents-get-tests-signatures

Generates a unique test signature from project, spec path, and test title.

currents-get-test-results

Fetches historical test execution results for a specific test signature.

currents-get-errors-explorer

Aggregates error metrics for a project with filtering and grouping capabilities.

currents-list-actions

Lists all actions for a project with optional filtering.

currents-create-action

Creates a new action for a project.

currents-get-action

Retrieves a single action by its ID.

currents-update-action

Updates an existing action.

currents-delete-action

Deletes (archives) an action.

currents-enable-action

Enables a disabled action.

currents-disable-action

Disables an active action.

currents-list-webhooks

Lists all webhooks for a project.

currents-create-webhook

Creates a new webhook for a project.

currents-get-webhook

Retrieves a single webhook by its ID.

currents-update-webhook

Updates an existing webhook.

currents-delete-webhook

Deletes a webhook.