{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"npm_npm-currentsmcp","slug":"npm-currentsmcp","name":"@currents/mcp","type":"mcp","url":"https://www.npmjs.com/package/@currents/mcp","page_url":"https://unfragile.ai/npm-currentsmcp","categories":["mcp-servers"],"tags":["currents","mcp-server","playwright","dashboard","reporting"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"npm_npm-currentsmcp__cap_0","uri":"capability://tool.use.integration.playwright.test.execution.via.mcp.protocol","name":"playwright test execution via mcp protocol","description":"Executes Playwright browser automation scripts through the Model Context Protocol, enabling Claude and other MCP clients to orchestrate end-to-end testing workflows. Implements MCP server transport layer that receives test execution requests, spawns Playwright browser instances, and streams test results back to the client with structured JSON responses containing pass/fail status, execution time, and error traces.","intents":["I want Claude to run my Playwright tests and interpret the results to debug failures","I need to automate browser testing workflows triggered by AI agents without manual intervention","I want to integrate my test suite into an AI-powered CI/CD pipeline that can reason about test outcomes"],"best_for":["AI agent developers building autonomous testing systems","Teams using Claude with MCP to automate QA workflows","Developers integrating Playwright tests into LLM-driven development loops"],"limitations":["No built-in test parallelization — executes tests sequentially through MCP transport","Requires Playwright to be installed in the same Node.js environment as the MCP server","No native support for test result persistence or historical trend analysis","MCP protocol overhead adds ~50-200ms latency per test execution request/response cycle"],"requires":["Node.js 18+","Playwright 1.40+ installed as a dependency","MCP client implementation (e.g., Claude with MCP support)","Playwright test files written in TypeScript or JavaScript"],"input_types":["test file path (string)","test configuration object (JSON)","browser launch options (structured data)"],"output_types":["test execution results (JSON with pass/fail status)","error traces and stack traces (text)","execution metrics (duration, memory usage)"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm_npm-currentsmcp__cap_1","uri":"capability://tool.use.integration.currents.dashboard.integration.via.mcp","name":"currents dashboard integration via mcp","description":"Exposes Currents test reporting dashboard data and controls through MCP tool definitions, allowing Claude to query test runs, retrieve execution summaries, and access failure analytics without direct API calls. Implements MCP resource handlers that map Currents API endpoints to structured tool schemas, enabling LLM clients to fetch dashboard metrics and interpret test health status programmatically.","intents":["I want Claude to check the status of my latest test run and summarize failures","I need an AI agent to query Currents dashboard data and trigger alerts based on test trends","I want Claude to analyze test execution history and recommend optimizations"],"best_for":["Teams using Currents for test analytics who want AI-driven insights","DevOps engineers building AI-powered monitoring dashboards","QA teams integrating test reporting into LLM-based decision workflows"],"limitations":["Read-only access to dashboard data — no capability to modify test runs or delete results","Requires valid Currents API credentials passed to MCP server at startup","Dashboard query latency depends on Currents API response times (typically 500ms-2s)","No real-time streaming of test results — only snapshot queries at request time"],"requires":["Currents account with API access enabled","Currents API token or authentication credentials","Network connectivity to Currents API endpoints","MCP client with tool-calling support"],"input_types":["test run ID (string)","project ID (string)","date range filters (ISO 8601 timestamps)","query parameters (JSON)"],"output_types":["test run summary (JSON with pass/fail counts)","failure details and error messages (structured text)","execution timeline and metrics (numeric data)","test health trends (time-series data)"],"categories":["tool-use-integration","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm_npm-currentsmcp__cap_2","uri":"capability://data.processing.analysis.test.result.streaming.and.structured.reporting","name":"test result streaming and structured reporting","description":"Captures Playwright test execution output and transforms it into structured JSON reports that MCP clients can parse and reason about. Implements event listeners on Playwright test runner that intercept test lifecycle events (start, pass, fail, skip), aggregate results with metadata (duration, error traces, assertions), and serialize to JSON format compatible with MCP response schemas.","intents":["I want Claude to receive detailed test failure information and suggest code fixes","I need structured test results that an AI agent can parse and correlate with code changes","I want to feed test execution data into an LLM for automated root cause analysis"],"best_for":["AI-driven debugging workflows where Claude analyzes test failures","Automated test report generation systems powered by LLMs","Teams building intelligent test failure triage systems"],"limitations":["Report generation adds ~100-300ms overhead per test depending on result complexity","Large test suites (1000+ tests) may produce JSON payloads exceeding MCP message size limits","No built-in compression — verbose error traces can inflate report size significantly","Requires Playwright test runner integration — incompatible with other testing frameworks"],"requires":["Playwright test runner configured in the same Node.js process","MCP server with JSON serialization support","Test files instrumented with Playwright assertions"],"input_types":["Playwright test execution events (internal)","test configuration metadata (JSON)"],"output_types":["structured test report (JSON)","error traces and stack traces (text)","test metrics (numeric: duration, memory, CPU)"],"categories":["data-processing-analysis","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm_npm-currentsmcp__cap_3","uri":"capability://tool.use.integration.mcp.server.lifecycle.management.and.transport","name":"mcp server lifecycle management and transport","description":"Implements the Model Context Protocol server specification, handling client connections, tool registration, request/response serialization, and error handling. Manages the MCP transport layer (stdio, HTTP, or WebSocket) that allows Claude and other MCP clients to discover available tools, invoke test execution, and receive results with proper error propagation and timeout handling.","intents":["I want to expose my Playwright tests as tools that Claude can call natively","I need a reliable MCP server that handles concurrent requests from multiple AI clients","I want proper error handling and timeouts so Claude doesn't hang on failed test runs"],"best_for":["Developers building MCP-compatible test automation infrastructure","Teams deploying Claude with custom MCP servers for testing","Organizations standardizing on MCP for AI-driven DevOps workflows"],"limitations":["Single-threaded execution model — concurrent test requests queue sequentially","No built-in authentication — relies on MCP client to provide credentials","Timeout handling is basic — long-running tests may exceed MCP client timeouts","No automatic reconnection logic — client must handle server restarts"],"requires":["Node.js 18+ with MCP SDK installed","@currents/mcp package from npm","MCP client implementation (e.g., Claude with MCP support)","Proper environment configuration for API credentials"],"input_types":["MCP protocol messages (JSON-RPC)","tool invocation requests (structured)"],"output_types":["MCP protocol responses (JSON-RPC)","tool results (JSON)","error messages (structured)"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm_npm-currentsmcp__cap_4","uri":"capability://memory.knowledge.test.execution.context.preservation.across.mcp.calls","name":"test execution context preservation across mcp calls","description":"Maintains browser state, session data, and test context across multiple MCP invocations, allowing Claude to run sequential test steps that depend on shared browser state. Implements session management that keeps Playwright browser instances alive between tool calls, preserving cookies, local storage, and DOM state so multi-step test scenarios can execute without reinitializing the browser.","intents":["I want Claude to run a multi-step test scenario where later steps depend on earlier browser state","I need to maintain login sessions across multiple test invocations","I want to avoid expensive browser initialization overhead when running related tests"],"best_for":["Complex end-to-end testing workflows requiring stateful browser interactions","Teams running multi-step test scenarios orchestrated by Claude","Applications with expensive setup costs (login, data seeding) that benefit from session reuse"],"limitations":["Session state is ephemeral — lost if MCP server restarts","No built-in session persistence to disk — requires external state management for durability","Memory overhead grows with number of concurrent browser sessions","Stale state can cause test flakiness if browser state isn't properly reset between unrelated tests"],"requires":["Stateful MCP server instance (not serverless/ephemeral)","Sufficient memory to maintain browser instances (typically 100-300MB per browser)","Test design that explicitly manages session lifecycle"],"input_types":["session ID or context identifier (string)","test step definition (JSON)"],"output_types":["test step result (JSON)","updated browser state metadata (JSON)"],"categories":["memory-knowledge","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm_npm-currentsmcp__cap_5","uri":"capability://data.processing.analysis.error.trace.extraction.and.ai.friendly.formatting","name":"error trace extraction and ai-friendly formatting","description":"Extracts detailed error information from failed Playwright tests and formats it for LLM consumption, including stack traces, assertion messages, DOM snapshots, and screenshot data. Implements error parsing that converts Playwright's native error objects into structured JSON with code context, line numbers, and relevant source code snippets, making it easy for Claude to understand and fix failures.","intents":["I want Claude to analyze test failures and suggest code fixes based on error details","I need detailed error context (stack traces, DOM state) formatted for LLM analysis","I want Claude to correlate test failures with recent code changes"],"best_for":["AI-driven debugging workflows where Claude analyzes test failures","Automated test failure triage systems","Teams using Claude to suggest fixes for failing tests"],"limitations":["Screenshot and DOM snapshot capture adds 500ms-2s per failed test","Large snapshots (>10MB) may exceed MCP message size limits","No built-in source code mapping — requires source maps for accurate line numbers","Error formatting is Playwright-specific — incompatible with other test frameworks"],"requires":["Playwright test runner with screenshot/trace capture enabled","Source maps or TypeScript source files for accurate error context","Sufficient disk space for temporary snapshot storage"],"input_types":["Playwright error objects (internal)","test execution context (JSON)"],"output_types":["formatted error report (JSON)","stack traces with source context (text)","DOM snapshots (HTML/JSON)","screenshot data (base64 or file path)"],"categories":["data-processing-analysis","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":37,"verified":false,"data_access_risk":"high","permissions":["Node.js 18+","Playwright 1.40+ installed as a dependency","MCP client implementation (e.g., Claude with MCP support)","Playwright test files written in TypeScript or JavaScript","Currents account with API access enabled","Currents API token or authentication credentials","Network connectivity to Currents API endpoints","MCP client with tool-calling support","Playwright test runner configured in the same Node.js process","MCP server with JSON serialization support"],"failure_modes":["No built-in test parallelization — executes tests sequentially through MCP transport","Requires Playwright to be installed in the same Node.js environment as the MCP server","No native support for test result persistence or historical trend analysis","MCP protocol overhead adds ~50-200ms latency per test execution request/response cycle","Read-only access to dashboard data — no capability to modify test runs or delete results","Requires valid Currents API credentials passed to MCP server at startup","Dashboard query latency depends on Currents API response times (typically 500ms-2s)","No real-time streaming of test results — only snapshot queries at request time","Report generation adds ~100-300ms overhead per test depending on result complexity","Large test suites (1000+ tests) may produce JSON payloads exceeding MCP message size limits","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.49742201635108657,"quality":0.22,"ecosystem":0.45,"match_graph":0.25,"freshness":0.52,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.15,"match_graph":0.23,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:23.903Z","last_scraped_at":"2026-05-03T14:23:33.671Z","last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":15349,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=npm-currentsmcp","compare_url":"https://unfragile.ai/compare?artifact=npm-currentsmcp"}},"signature":"Hrl8nmPsqkZxIoff8m4Q9FyPdEy1L97Wue0oq2xgzxTTxw7OVYKFXn2tLASF+/iVUYFIHN6r6VZ7/T1RZpniCA==","signedAt":"2026-06-23T09:19:58.104Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/npm-currentsmcp","artifact":"https://unfragile.ai/npm-currentsmcp","verify":"https://unfragile.ai/api/v1/verify?slug=npm-currentsmcp","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}