"An agent for conducting research" matching MCP servers:

Agent Ready is an AI agent readability scanner — point it at any public URL and get back a 0–100 score plus per-check remediation hints for every failing check. This package wraps the same engine that powers agent-ready.dev as an MCP server, so Claude Desktop, Claude Code, Cursor, Cline, VS Code, and Windsurf can run scans inline and explain the results.

Scans any website to generate an Agent Readiness Report based on the ASO framework, evaluating agent discoverability, trust, interoperability, and commerce readiness.

Enables AI agents and MCP clients to drive real Chrome, Edge, Brave, and Firefox browsers through native automation protocols. It exposes tools for navigation, page snapshots, form filling, clicks, screenshots, console/network inspection, and tab management.

MCP server that gives an AI agent a throwaway test identity — a real disposable email address and a real UK phone number — so it can sign up for something it's testing and read back the verification email/SMS itself, without a human in the loop.

Enables building and evaluating LangGraph agents over a protocol-level MCP server to measure failure rates across four agent topologies.

Analyzes Playwright test results to provide structured QA insights, including test metrics, failure analysis, bug report drafts, and release-quality recommendations.

Provides read-only tools to generate test plans for AI agents, score agent runs, and produce reusable evaluation scorecards.

An MCP server that lets an AI agent drive the iOS Simulator in a loop, enabling tapping, typing, swiping, reading the screen via the accessibility tree, and verifying app state.

Provides tools for managing tasks, searching docs, and running a heuristic quality gate to check agent output for common issues before human review.

Enables an AI agent to boot and control an Android emulator — tapping, typing, scrolling, inspecting screens, reading logs and installing APKs — and to record those interactions as replayable, CI-ready test flows. Actions are captured by element text or id rather than coordinates, so the saved tests survive layout changes and rerun without the agent.

MCP server exposing AI agent observability tools: list, inspect, and deterministically replay recorded agent execution traces for debugging failures.

Enables AI clients to analyze software test results and defect records, producing explainable GO, CONDITIONAL_GO, or NO_GO release-readiness recommendations with deterministic risk scoring, failed-test retrieval, defect hotspot ranking, and regression test planning.

An MCP-style stdio server for evaluating AI agent outputs, enabling CI-friendly quality gates, regression comparisons, and canary promotion decisions.

MCP server for operating and testing Android devices with AI agents. Provides observation and action tools for interactive control and spreadsheet-driven test runs.

Enables MCP-compatible clients to execute Playwright-based UI and API test suites (login, inventory, checkout, API, regression) and receive structured JSON test results.

A local MCP server that gives Cursor Agent three focused QA tools for analyzing user stories, creating test charters, and drafting bug reports, with built-in safety rules and reusable workflows.

Exposes three read-only tools that list local Agent and MCP runtime candidates, inspect running processes, and check a live runtime against an approved artifact expectation. Returns explicit verdicts such as matched, stale, leaked, conflict, unknown, or not running without exposing argv, environment values, or file contents.

Lets an AI coding agent journal its edits, commands, checkpoints, intents and test evidence locally, then compile them into a machine-readable Change Package plus a human-readable review summary with statically computed risks. Optionally publishes the result as a GitHub Draft PR with inline comments on the exact diff lines, always gated behind explicit confirmation and redaction.

Enables reviewing grant application text, running deterministic eval cases, and executing Office of Research Aid packet workflows through MCP.

Provides a hand-written MCP server integrated with a LangGraph agent to benchmark multiple agent topologies and measure their failure rates.

An MCP server that lets an AI agent drive and inspect a running Next.js app, with headless route/error introspection and a real DOM-based in-page bridge for interactive testing.

Enables AI-driven mobile test automation through planning, generation, and self-healing agents for Android and iOS, exposed as callable MCP tools.

Enables users to run synthetic support-agent evaluations, preserve and inspect traces, score results deterministically, inject failures, and enforce release review gates through MCP tools, resources, and prompts.

Serves MCP tools to inspect agent trace JSONL files and evaluate them against golden-case constraints, returning structured metrics and gate results.

Enables capturing web evidence, freezing content-addressed snapshots, and comparing research agents on the same sources with traceable access and quotations.

Enables MCP clients to compile natural-language intent into a validated executable agent contract and to validate existing contracts through two exposed tools.

Deploys a self-hosted Cloudflare email service providing short-lived mailboxes with a JSON API and MCP endpoint for automated testing and AI agent signup, verification, and magic-link flows.

Self improving QA agent for software teams

Enables users to retrieve Agent Failure-Recovery SLA terms, check agent compliance and credit history, and run adversarial chaos tests against agent infrastructure.

MCP server for recording, replaying, and comparing agent sessions to debug non-deterministic behavior and detect divergence.