Introducing Currents MCP Server
Connect your AI tools to Currents using MCP
Today, we’re excited to share the first version of Currents MCP server. You can use this server to connect agents like Cursor, Claude or VS Code directly with Currents.
What is MCP?
MCP stands for Model Context Protocol. It's an open pattern, introduced by Anthropic, that provides a consistent way for systems to expose tools and resources that can be used by AI models.
In our case, Currents MCP server acts as a context layer for any tool that can leverage information about a run, such as the spec list, failed tests, errors, and more.
Currents MCP
Our first version of the MCP server is intentionally simple, but already quite powerful.
Tools
Currents MCP server expose two tools:
- Get high-level details of a run
- Get deep details of a run's test attempts
These tools enable the AI model to get information like:
- ✅ The overall status (passed/failed)
- 🧪 Which specs failed
- 🔁 Whether any of them were flaky
- 🐛 Error messages and stack traces
- 📄 Metadata useful for debugging (e.g., retries, duration, environment)
For more details on the data, refer to the Run Details API and Instances API.
Vibe-fix failing testings 😜
Read our Setup Guide to get started with Currents MCP.
Here is what the workflow looks like:
- A test run fails in CI.
- You ask an AI agent to help you fix the failing tests.
- Currents exposes details about the run and the failed tests via the MCP server.
- The AI agent consumes that context and proposes a code change.
- The user can then trigger a new test run, and ask the AI agent to verify the fix.
This cycle drastically cuts down on the time developers spend manually digging through logs to figure out what broke.
What’s Next
This is just the beginning. Here’s what we’re exploring next:
- 🔄 Allowing the AI to re-run failed tests for you.
- 🤖 Bi-directional feedback loops (MCP automatically validates that a fix worked).
- 📊 Exposing historical performance data to allow the AI to optimize tests.
If there’s something else you’d love to see, let us know — we’re building this in the open, and your feedback shapes the roadmap.
Join the growing community of teams using Currents for their Cypress and Playwright tests
Trademarks and logos mentioned in this text belong to their respective owners.