"How to access a web browser" matching MCP servers:

coldstart gives coding agents durable memory of a specific codebase, with no embeddings, no vector store, and no API key. Agents write notes after real tasks — what a file is for, how a flow spans files, which invariants hold — and those notes are surfaced automatically to a later session whose task matches, so nothing gets rediscovered from scratch. Every note is anchored to real files by content

RCP-1 is an enterprise-ready MCP server that connects AI assistants to SAP ABAP systems via the ADT REST API, with built-in security, access controls, and deployment options for BTP or on-premise.

Call graph MCP server for Rust, Python, TypeScript, TSX, and JavaScript. Every caller and callee carries a resolution field showing how the reference was matched to a definition, plus multi-hop impact analysis for refactoring. Local-only, single binary, no network egress. Benchmarked against grep, ripgrep, and ctags on a 120-item hand-verified golden set, including the cases where it loses.

AI-powered QA testing platform — catches JS errors, accessibility failures, visual regressions, API loops, security issues, and more via Chrome DevTools MCP

Offers a control surface for AI agent security with four independent checks: source-code scanning, tenant isolation, LLM content verification, and deploy gating. Currently in pre-release, with no functional scanning engines yet.

A local-first MCP server that scores your codebase's Build Readiness by reading code and running tests on your machine, outputting a diligence-grade score and risk register without uploading your source.

AI reads your codebase like a book - one page at a time. Pharaoh gives it the index and a map of how every chapter connects.

Enables AI-assisted X++ development for Dynamics 365 Finance and Operations by pre-indexing the entire codebase and providing 54 specialized tools for metadata lookup, code generation, and best practice validation.

Gives AI coding tools access to the CSS cascade the way DevTools does — which rules matched, which won, where each came from.

Provides a read-only interface to audit and continue coding agent sessions by extracting plans, intents, and edit authorship from history across multiple agents (Claude, Codex, OpenCode, Antigravity, Pi) via MCP, CLI, and Python SDK.

Enables AI assistants to access Macroforge documentation, validate TypeScript code with @derive decorators, expand macros, and retrieve macro documentation.

A code review tool server based on Model Context Protocol (MCP) providing multi-dimensional code review and scoring.

locidx

MCP server for writing World of Warcraft addons, providing in-game Lua API references, Blizzard's UI source code, and game asset data to AI assistants.

An installable MCP server that reviews diffs/PRs against a target repository's own coding conventions, learned via RAG over its code, docs, and lint config, citing specific file:line sources.

Enables headless control of a DOSBox-X guest, including memory reading and patching, framebuffer capture, input injection, and live code tracing without interfering with the host desktop.

Enables AI agents to formally verify constant-time, masking, and patch completeness properties of Verilog hardware designs, providing concrete leakage signals and next-step guidance.

A lightweight MCP server that provides 40 tools for TypeScript/JavaScript refactoring and code intelligence, directly mapping to TypeScript's tsserver protocol commands for accurate structural changes and workspace analysis.

Enables an MCP-capable assistant to review GitLab merge requests, GitHub pull requests, and pre-push local branches against ticket requirements, domain rubrics, compiler/lint pre-passes, blast-radius analysis, and SonarQube findings, and to draft inline comments or follow-up tasks in the user's chosen language. Nothing reaches a remote host until a human approves the exact content in an interactive terminal.

Enables AI agents to perform read-only static analysis of Node.js backend projects, detecting database query anti-patterns, async bottlenecks, connection pooling mistakes, and dependency hygiene issues while returning structured evidence-backed findings.