"A server for deep research and in-depth exploration of topics" matching MCP servers:

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

MCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.

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

MCP server providing tools to verify task completion (tests pass and changes match claim) and confirm bug reproduction before fixing.

Enables MCP clients to open websites, capture screenshots at multiple breakpoints, and run automated design audits for issues like overflow, small tap targets, low contrast, missing alt text, tiny text, and clipped content.

A validation layer for AI coding assistants that enforces explicit LLM evaluations on plans, code diffs, and tests to ensure safer and higher-quality code.

Enables deliverable conformance and evidence-chain checks by turning requirements into executable specs, validating numbers against a provenance ledger, and auditing PDF/OOXML metadata and archive manifests.

Unified MCP server for DeepAgentLabs that exposes workflow profiling, analysis, and chaos experiment tools through a single interface.

MCP-first A/B testing server that enables agents to manage experiments (create, update traffic splits, read results, apply winning variants) from tools like Claude Code, with self-hosted Cloudflare backend.

MITM proxy MCP server that intercepts and verifies AI agent tool calls, detecting fabrication, tracking costs, verifying outcomes, and inferring user satisfaction.

Zero-sidecar MCP server embedded directly in the Godot 4 editor as a GDScript EditorPlugin — no Node or Python sidecar. Reflection-driven tools over any engine class, validate-before-write GDScript, scene/script/resource authoring, and a runtime play-test loop (play, screenshot, input, assert).

Lets an assistant read recorded production AI agent runs — steps, model and tool calls with arguments, and outcomes — along with the findings of comparison runs that checked a prompt or model change against those recordings, and verify a signed evidence bundle offline with no account or network. It is strictly read-only: no tool starts a replay or comparison, so nothing can spend money or act without a person deciding.

A simple server implementing the Model Context Protocol (MCP) that echoes messages back, designed for testing MCP clients.

Bridges AI models with WinDbg to analyze Windows crash dumps and perform remote debugging through natural language queries, enabling execution of debugger commands and automated crash analysis.

Validates .mcp.json and claude_desktop_config files to catch duplicate server names, missing binaries, invalid environment variables, and unreachable endpoints. Reports each problem along with how to fix it, so silently failing MCP servers can be diagnosed and repaired.

MCP server for remote debugging of Apps in Toss mini-apps, providing CDP relay and test runner capabilities.

Maps Electron app IPC handlers to MCP tools and provides 33 built-in CDP tools for DOM automation, screenshots, interaction, and debugging, enabling Claude Code to directly control your Electron app.

Enables LLMs to perform browser automation tasks including web scraping, taking screenshots, and executing JavaScript using Playwright. It facilitates real-time interaction with web pages and the generation of automated test code.

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.

Generates a pytest suite from acceptance criteria that are withheld from the coding agent, so the tests can disagree with the code. Four tools, and qikly_run never returns the criteria, which a test in the suite enforces.