概要
What is Currents MCP Server?
The Currents MCP Server connects AI coding agents (like Cursor and Claude) directly to the Currents dashboard, giving them full visibility into CI test results so they can diagnose flaky tests, pinpoint failures, and act on real execution data without leaving the editor.
How to use Currents MCP Server?
Obtain a Currents API key, then configure the server in your MCP client. For Cursor, add the @currents/mcp command and CURRENTS_API_KEY environment variable to mcp.json. For Claude Desktop, edit claude_desktop_config.json similarly. For Claude Code, run claude mcp add with the same parameters.
Key features of Currents MCP Server
- Query runs, spec files, and individual test results from CI.
- Surface error trends and performance metrics across your test suite.
- Manage quarantine rules, webhooks, and project settings programmatically.
- Create, link, and list Jira issues using the organization Jira integration.
- Cancel, reset, or delete runs directly from the MCP tools.
- Get aggregated error metrics and failure context for AI debugging.
Use cases of Currents MCP Server
- Diagnose and fix flaky tests by examining actual CI output through an AI agent.
- Programmatically manage project configuration (webhooks, actions, rules) from the editor.
- Automatically create Jira issues from failing tests to track technical debt.
- Monitor test suite health by querying aggregated performance metrics.
- Allow agents to cancel or reset stuck runs without switching to the Currents dashboard.
FAQ from Currents MCP Server
What runtime or dependencies are required?
The server runs via npx -y @currents/mcp, which requires Node.js and npm (typically bundled with Node). No additional installation beyond the MCP client setup is needed.
How is data authenticated and secured?
Authentication uses a CURRENTS_API_KEY environment variable. By connecting AI tools via MCP to Currents, you grant them access to your API key, test results, and CI metadata. It is your responsibility to vet any AI agents or services you use.
Where does test execution data live?
All test execution data resides in the Currents cloud platform. The MCP server queries the Currents API to retrieve it; no local storage of test results is described.
What transport protocol does it use?
The MCP server uses the stdio transport, as shown by the command and args configuration in all setup examples.
Can the server create or delete project resources?
Yes. Tools include creating, updating, and deleting actions and webhooks, as well as deleting runs and cancelling or resetting them.
