"Developing agents with expertise in the latest documentation" matching MCP servers:

Provides a stable, side-effect-free MCP tool contract that enables AI workflows to be prototyped, demoed, tested, or dry-run without connecting to databases, APIs, files, or other real data sources. It enables swapping in a real data server later without changing the AI-facing interface.

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.

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.

Enables AI agents to inspect UI screen recordings as token-efficient image sheets with changed regions boxed, single-frame flicker flagged, and speech aligned to frames. Exposes watch_video and zoom_video tools so agents can pull dense keyframes across any time range or one sharp full-resolution frame, all processed locally.

Enables MCP clients to run and track scans, inspect quota usage, redeem existing studio report rights, and list or download generated reports through the associated REST API. It operates locally over stdio with API-key authentication and bounded retry/polling behavior.

Enables automated QA testing by running a pipeline of AI agents that generate test scenarios, architect test layers, write Playwright tests, and review code, all grounded in feature requirements and API contracts.

Exposes 11 agent-native QA tools over stdio so coding agents can discover a project, analyze risk, select the smallest relevant test set, generate and dry-run tests, triage failures, propose tiered heals, analyze flakes, generate quality reports, and evaluate release readiness. Planning and healing tools stay read-only or propose-only, while execution defaults to dry-run, keeping agent actions safe and evidence-backed.

Provides a read-only MCP bridge that lets Claude Web inspect workspace files, git state, and recorded test results while Codex remains the sole executor of changes.

Enables AI agents in Copilot Chat to autonomously plan, generate, and self-heal Playwright UI and API tests by connecting to a local browser runtime.

Enables MCP clients and agents to query synthetic football match state, key moments, win probability, and player profiles, and to verify claims and on-screen overlay numbers against match state.

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.

Enables AI agents to submit code files for analysis and receive rule-based findings with severities, line numbers, and SARIF fingerprints, covering security, complexity, and dependency/configuration drift.

Enables free, read-only checks of AI agents and MCP servers for conformance, published changes, delivery evidence, and verifiable receipts without requiring an account or API key, using public or non-personal data only.

Enables AI agents to create webhook URLs, wait for incoming deliveries, inspect payloads, and replay or send signed webhook events to a local handler.

Free, MIT-licensed MCP testing harness with Jay: risk-based testing workflows, exploratory and regression checks, accessibility investigation, bug triage, disposable demos, and protected local evidence reports. Runs locally via @testers-ai/carbon-mcp; the coding agent supplies model, browser, and shell access, and analytics defaults off in the npm edition.

Enables AI agents to validate .tdc configs, generate deterministic test data files locally, locate language and country data packs, summarise generated files, and read the TDCv2 docs as MCP tools. Everything runs on the user's machine, producing identical output byte for byte on every run.

MCP server that integrates sql-sop SQL linter into LLM clients, enabling linting SQL queries and listing lint rules via chat tools.

Primarily to be used as a template for developing MCP servers with FastMCP in Python, PyMCP is somewhat inspired by the official everything MCP server in Typescript.

Provides a framework for running multiple MCP servers using FastAPI, stdio, and streamable-http transports, with an echo tool for testing and integration with MCP Inspector.

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