---
title: "currents"
description: "Currents gives AI agents the test results your CI records, from Playwright, Vitest, Jest and more. Self-healing tests: an agent gets the errors, traces and history behind a failure, finds the root cause and fixes the tes"
canonical: https://agentpluginsdirectory.com/plugins/currents
last-updated: 2026-10-23
---

# currents
Currents gives AI agents the test results your CI records, from Playwright, Vitest, Jest and more. Self-healing tests: an agent gets the errors, traces and history behind a failure, finds the root cause and fixes the test, flaky ones included. Proof of work for any change, not just tests: before-and-after screenshots, videos and Playwright traces from CI, or a demo the agent records in a browser, posted as evidence in the pull request. Teams also use it to reproduce bugs, verify fixes, rank flaky and slow tests, quarantine tests and integrate with GitHub, Gitlab, Slack, Jira, Linear and more.
- Slug: currents
- Publisher: Currents
- Repository: https://github.com/currents-dev/currents-mcp
- Manifest: plugin.json
- Version: 1.0.0
- License: Apache-2.0
- Category (editorial): other
- Skills: 3 (browser-evidence, collect-evidence, fix-failing-tests)
- MCP servers: 1 (currents)
- Stars: 21
- Repository created: 2025-04-02
- Repository last pushed: 2026-10-21
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/currents
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What currents does, in the publisher's words

Give your AI coding agents full visibility into your CI test results. The Currents MCP Server connects tools like Cursor and Claude directly to your Currents dashboard, so agents can diagnose flaky tests, pinpoint failures, and act on real execution data, without leaving your editor.

- 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
- Let agents fix what's broken using actual test output, not guesswork

Agent skills that teach AI agents multi-step Currents workflows.

The server publishes every skill as an MCP resource, so a connected agent can list and read them without a local copy:

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/currents-dev/currents-mcp/HEAD/README.md

## MCP servers

- currents: transport: streamable-http; url: https://mcp.currents.dev/mcp

Read from the plugin's own mcp.json. Environment variable names only, never values.