@currents/mcp

Exposes Playwright test execution as MCP tools, allowing Claude and other LLM clients to invoke browser automation workflows through a standardized tool-calling interface. Implements a schema-based function registry that maps Playwright operations (navigation, interaction, assertion) to callable MCP resources with structured input/output contracts, enabling LLMs to compose multi-step browser automation sequences without direct SDK knowledge.

Exposes Currents cloud test reporting platform as MCP callable tools, enabling LLM clients to query test runs, retrieve failure summaries, and access CI/CD test metadata without direct API calls. Implements a schema-based wrapper around Currents' REST API that translates test result queries into structured MCP tool calls, with built-in filtering, pagination, and result formatting for LLM consumption.

Implements the Model Context Protocol server specification, handling client connection negotiation, tool schema registration, and request routing. Uses a declarative tool definition system where each Playwright or Currents operation is registered as an MCP tool with JSON Schema validation, enabling clients to discover available capabilities and invoke them with type-safe parameters.

Enables Playwright test execution to capture screenshots and expose them as base64-encoded data or file references through MCP tools, allowing LLMs to perform visual assertions and analyze UI state. Integrates with Playwright's screenshot API to capture full-page, element-specific, or viewport-only images, with optional comparison against baseline images for regression detection.

Automatically extracts and structures error messages, stack traces, and browser console logs from failed Playwright tests, enriching them with contextual metadata (test name, duration, browser type) for LLM consumption. Implements a parsing layer that normalizes error output across different assertion libraries (Playwright's built-in assertions, Chai, Jest) and formats them as structured JSON for easier LLM interpretation.

Manages Playwright browser contexts and sessions across multiple MCP tool invocations, enabling stateful test workflows where subsequent operations inherit browser state (cookies, local storage, authentication) from previous steps. Implements a context registry that persists browser instances and page objects between tool calls, allowing LLMs to compose multi-step workflows without re-initializing the browser for each step.

Queries Currents API to retrieve CI/CD metadata associated with test runs (commit hash, branch, build ID, author), enabling LLMs to correlate test failures with code changes and build context. Implements a metadata enrichment layer that combines test result data with Git and CI/CD information, providing LLMs with full context for root-cause analysis and impact assessment.

Analyzes historical test execution data from Currents to identify flaky tests (tests that fail intermittently) and track failure trends over time. Implements statistical analysis of test pass/fail rates across multiple runs, with configurable thresholds for flakiness detection and trend visualization data for LLM interpretation.