"Two agents working simultaneously" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
MCP-native AI browser testing for coding agents. Submit a URL + goal, get back action trail, bugs, screenshots, and WebM video your agent patches from directly. 43 tools, 12 AI evaluation personalities, combo tiers with auto-pause-on-bugs, throwaway email + SMS inboxes.
Behind Second Look (preview): a shop's product page as clean data, source checks, price history.
A webhook inbox for agents: one call returns a live URL. Mock, verify, inspect and replay.
Disposable email addresses for tests and agents: register, wait for mail, extract codes and links.
GodPrompt MCP + Agent Skill for coding agents with TDD, debugging, verification, and task routing.
Paid deterministic data-quality and execution-verification tools for AI agents.
QA platform for agents: coverage signals, in-repo test plans, verified tests and release governance.
Run EPUBCheck for EPUB specification errors and compare two exports.
Zero-config agent-readiness auditor and Flight Simulator tools for AI coding agents
Pine Script backtest-trap checks, backtest reconciliation and official Korean finance data.
Webhook, email, WebSocket and tunnel testing for AI agents: capture, wait, verify, replay.
UI Verify is visual regression testing built for coding agents. Connect the MCP server and your agent (Claude Code, Cursor, Codex) pulls a pull request's UI changes into the conversation, views each visual diff, reads the AI judge's verdict of regression vs intended change, and accepts the intended baselines - all over MCP.
Testing, benchmarking and auditing autonomous AI agents — methods, harnesses, evidence
Evidence-gated task verification for AI agents. Decompose goals into acceptance criteria, attach proof (screenshot, curl, file), independent LLM judge accepts or rejects. 24 tools. Hosted remote MCP (streamable-http, OAuth 2.1 + DCR).
A real Android phone in the cloud for MCP agents: observe the screen, act, reset to a saved state.
Reconstruct helps AI coding agents recreate digital products with high visual and functional fidelity, or combine ideas and interface patterns from multiple products into a new experience. Agents work from captured evidence and verify the result against real references instead of guessing from screenshots. The MCP server provides screenshots, element trees, measured layouts, computed styles, typography, assets, routes, recorded user flows and frontend technology insights. It exposes 60 tools, 16 resources and nine workflow skills for inspecting, designing, building and verifying products in the user’s stack. Access uses browser-based OAuth and requires a Reconstruct account. Captured content is treated as untrusted reference data; new capture requests are submitted only when the user asks.
Workflow planning, recovery checkpoints, coordination, fixtures, and compatibility tools for agents.
Pre-launch website QA: deterministic rule-based scans, readiness score, and blockers for agents.
A deterministic verification engine for agents. Proves a fix: fails on the old code, passes on new.
Fail-closed, change-aware verification for AI coding agents with affected-test guidance.
