Currents
Enable AI Agents to fix Playwright test failures reported to Currents.
Currents MCP Server
This is a MCP server that allows you to provide test results context to your AI agents by connecting them to Currents. Useful for asking AI to fix or optimize tests failing in CI.
Tools
| Tool | Description |
|---|---|
currents-get-projects | Retrieves a list of all projects available. |
currents-get-runs | Retrieves a list the latest runs for a specific project. |
currents-get-run-details | Retrieves details of a specific test run. |
currents-get-spec-instances | Retrieves debugging data a specific execution of a test spec file. |
currents-get-spec-files-performance | Retrieves spec file historical performance metrics for a specific project. |
currents-get-tests-performance | Retrieves test historical performance metrics for a specific project. |
currents-get-tests-signatures | Retrieves a test signature by its spec file name and test name. |
currents-get-test-results | Retrieves debugging data from test results of a test by its signature. |
Setup
API Key
Get a Currents API key by following the instructions here.
Usage with Cursor Editor
- Go to Cursor Settings > MCP > Enable
- Add the following to your
mcp.json.
NPX
{
"mcpServers": {
"currents": {
"command": "npx",
"args": [
"-y",
"@currents/mcp"
],
"env": {
"CURRENTS_API_KEY": "your-api-key"
}
}
}
}
Usage with Claude Desktop
Add the following to your claude_desktop_config.json:
NPX
{
"mcpServers": {
"currents": {
"command": "npx",
"args": [
"-y",
"@currents/mcp"
],
"env": {
"CURRENTS_API_KEY": "your-api-key"
}
}
}
}
⚠️ Notice
By connecting AI tools (e.g., via MCP) to Currents, you are granting them access to your API key, test results and CI metadata. It is your responsibility to vet any AI agents or services you use, and to ensure they handle your data securely.
How to Contribute
We welcome contributions of all kinds—bug fixes, features, and documentation updates!
Quick Start
- Fork this repository and clone your fork:
git clone https://github.com/<your-username>/currents-mcp.git cd currents-mcp - Install dependencies:
cd mcp-server npm install - Build the project:
npm run build - Run tests:
See TESTING.md for more details on testing.npm test - Run locally (stdio):
You should see:npm startCurrents MCP Server running on stdio.
Local Development with a Client (optional)
To test with a local MCP client (e.g., Cursor or Claude Desktop), point the client to your built server:
- Command:
node - Args:
./mcp-server/build/index.js - Env: set
CURRENTS_API_KEYto a valid key
Example snippet for a client config:
{
"mcpServers": {
"currents": {
"command": "node",
"args": ["./mcp-server/build/index.js"],
"env": {
"CURRENTS_API_KEY": "your-api-key"
}
}
}
}
Test tools locally
To test the tools locally without any LLM, you can use the following command:
npm run build
then run the tools script:
node scripts/call-tools.js
Making Changes
- Create a feature branch:
git checkout -b feat/short-description - Make changes under
mcp-server/src/, then rebuild and re-run:npm run build && npm start - Write tests for your changes in
*.test.tsfiles alongside your code - Run tests to ensure everything works:
npm test - Keep changes focused and documented (add comments/types where helpful).
Commit and PR Guidelines
- Write clear commit messages (e.g., “fix: handle missing env vars” or “feat: add get-run tool filters”).
- Push your branch and open a Pull Request:
git push origin feat/short-description - In your PR, describe the motivation, approach, and any trade-offs. Link related issues if applicable.
Reporting Issues
- Before creating a new issue, please search existing issues to avoid duplicates.
- When filing a bug report, include steps to reproduce, expected vs. actual behavior, and environment details (OS, Node.js version).
License
By contributing, you agree that your contributions will be licensed under the ISC license (as specified in the package metadata).
Related Servers
Javadoc MCP
A Model Context Protocol (MCP) server for searching Java documentation. This server enables AI assistants to search and retrieve Java API documentation from JSON files.
AltTester® AI Extension
MCP server for game test automation
Financial Dashboard with AI Agent Integration
A financial dashboard for monitoring and analyzing investment portfolios with AI-powered insights.
MCP-Allure
Reads Allure test reports and returns them in LLM-friendly formats for better test analysis and insights.
Bonk MCP
Implements Solana blockchain functionality for the LetsBonk launchpad.
Elementor MCP Server
Perform CRUD operations on Elementor page data for a target WordPress website.
Yellhorn MCP
An MCP server that integrates Gemini 2.5 Pro and OpenAI models for software development tasks, allowing the use of your entire codebase as context.
Dart MCP
An example MCP server built with Dart and deployed on Cloudflare Workers.
Universal MCP Server
A universal MCP server with a modular plugin architecture.
Structurize-MCP
Generates structured CSV files from natural language descriptions using Google Gemini AI.