"How to interact with and read the browser tool console and DOM" matching MCP servers:

Enables LLMs to read and write local user data, generate fake users via sampling, and interact with structured prompts and resources.

Relays a result screenshot to Slack so you can review a coding agent's output without opening the app.

Enables AI agents to record and time-travel through DOM mutations, inspect and interact with live pages, capture screenshots, and diagnose UI disappearance or layout changes through a 34-tool MCP interface.

Enables async-first working practices by providing tools to draft decision docs, convert meetings to async artifacts, score status updates, and triage sync vs async tasks. It also offers reference tools for the Open and Async book's principles and coaching prompts.

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

Enables QA to interactively inspect DOM elements in a visible browser, generate resilient Robot Framework locators and Page Objects, and validate selectors via natural language.

Drives a real Chromium browser to extract a page's DOM into compact Semantic JSON with Playwright-native locators, enabling AI agents to generate consistent, accurate Playwright tests.

Enables document conversion between PDF, DOCX, and Markdown formats to facilitate reading and editing complex files in AI tools like Claude Desktop or Cursor. It utilizes marker-pdf and pandoc to provide structured text versions of documents, helping to manage context and support unsupported file types.

Monitor failing GitHub Actions workflows, auto-fix them with OpenCode, and retry the run — driven by a workflow_run webhook, coordinated through an MCP server.

Provides access to the Reuters Business and Financial News API to retrieve articles, trending news, and market data. It enables searching and filtering financial content by date, author, category, and keywords.

MCP server that converts file contents into compact, line-numbered PNG images for vision models to read, reducing token usage by roughly 7x for large files.

Enables MCP clients to search, describe, and call roughly 180 undocumented UniFi OS/Network console API operations from a bundled OpenAPI spec, plus curated reads and typed configuration changes. Writes are off by default, require per-entity enablement, and use previews, verification, and rollback safeguards.

Agent-native browser control MCP server that enables AI agents to browse and interact with web pages via accessibility tree snapshots and ref ID-based commands.

MCP server that exposes GDB debugging as tools. An AI assistant can set breakpoints, run programs, step through code, inspect variables and memory, and examine registers — all via structured tool calls. Reverse debugging with rr is also supported.

A read-only MCP server for Google Search Console that lets you query search performance data, sitemaps, and URL index status from any MCP client.

Enables AI assistants to read and search Kafka messages through the Redpanda Console HTTP API, including topic listing, message fetching by offset or time, and substring search, without direct Kafka broker access.

Captures browser console messages (log, warn, error, etc.) and makes them available to AI language models like Claude Code and Gemini CLI for seamless debugging and development.

Multi-account Google Search Console MCP server enabling AI assistants to query multiple GSC accounts by name in a single session, with support for OAuth and service accounts.

An MIT MCP server and CLI with 43 tools for Search Console, the App Store, Google Play and WordPress.org. A missing row is reported as unknown, never as zero.

An enhanced browser automation MCP server that solves token limit issues through intelligent semantic compression, enabling universal web automation with context-aware snapshot modes.