aicoolies logo

Safari MCP Server

Apple's Safari-native MCP server for web debugging agents

Share
freeTelemetry Concerns
Visit Website →

Safari MCP Server is Apple's safaridriver-based MCP server in Safari Technology Preview, giving compatible coding agents local access to Safari page content, console logs, network requests, screenshots, JavaScript evaluation, interactions, viewport controls, and accessibility/performance checks.

Safari MCP Server is Apple's WebKit MCP server for connecting compatible coding agents to a live Safari Technology Preview window. It runs locally through Safari Technology Preview's safaridriver with the --mcp flag, so an MCP-aware agent can inspect browser state that would otherwise have to be described manually in a prompt or screenshot.

The official WebKit launch describes browser-context tools for page content, DOM-oriented interactions, console messages, network request details, screenshots, JavaScript evaluation, tab management, navigation, viewport size, CSS media emulation, dialogs, accessibility signals, and performance-oriented debugging. That makes the tool most useful when a team needs an agent to reason about real Safari rendering, WebKit compatibility, logged-in app state, layout regressions, or browser-specific front-end behavior.

Treat Safari MCP Server as a developer-preview workflow rather than a production browser-automation cloud. WebKit says the server makes no network calls of its own and does not expose Safari personal information such as AutoFill or unrelated browser activity, but captured page data is still handed to the local agent and then follows that agent or model provider's security boundary. Keep access limited to trusted local agents and avoid mixing the official Apple/WebKit workflow with older community Safari MCP packages.

Pricing

Free Safari Technology Preview developer preview from Apple. Requires a supported macOS release and enabling remote automation/external agents; no managed-service pricing was found in current Apple or WebKit docs.

Platforms

Local Safari Technology Preview safaridriver --mcp workflow for MCP-compatible coding agents on macOS.

Categories

Tags

Use Cases

Related Tools

Headroom

Context compression for LLM apps and coding agents

Headroom is an Apache-2.0 context compression layer for LLM apps and coding agents. It compresses tool output, logs, files, RAG chunks, and agent history through a local library, proxy, wrapper, or MCP server, with retrieval hooks for bringing originals back when needed. Treat its savings numbers as Headroom-reported benchmarks, not independent aicoolies measurements.

open-sourceOpen SourceTelemetry

Codebase Memory MCP

Codebase knowledge graph MCP server for AI coding agents

Codebase Memory MCP is an MIT-licensed MCP server that turns a repository into a persistent code knowledge graph for AI coding agents. It gives Claude Code, Cursor, Codex-style agents, and other MCP clients structural queries for functions, classes, call chains, routes, and architecture, helping them explore large projects without repeatedly rereading files or relying only on broad search.

open-sourceOpen SourceTelemetry

Supabase MCP

MCP server for connecting AI assistants to Supabase projects

Supabase MCP is Supabase's Apache-2.0 server for connecting AI assistants to Supabase projects. It can expose database, configuration, and project-management workflows to MCP clients such as Cursor, Claude, and Windsurf, while the official docs emphasize permission and security review before production use, SQL changes, or high-privilege database access.

open-sourceOpen SourceTelemetry

Notion MCP Server

Official Notion MCP server for AI-agent workspace access

Notion MCP Server is Notion's official MIT-licensed MCP server for connecting AI assistants to Notion workspaces. It supports the vendor-backed remote OAuth path and tools designed for page, workspace, and Markdown-style operations, making it a safer default than unofficial Notion bridges for teams already using Notion for docs, projects, or internal knowledge bases.

open-sourceOpen SourceTelemetry
Klavis AI logo

Klavis AI

MCP integration platform for agent tool use at scale

Klavis AI is an Apache-2.0 MCP integration platform for teams connecting AI agents to external SaaS tools and APIs. The public repo and official docs position it as infrastructure for reliable tool access at scale, so it fits teams that want reusable MCP connectors without treating every integration as a one-off script or custom OAuth maintenance project.

open-sourceOpen SourceTelemetry
Superserve logo

Superserve

Open-source Firecracker sandboxes for long-running AI agents

Superserve is an open-source sandbox infrastructure layer for AI agents that need durable computers instead of short-lived shells. It runs isolated Firecracker microVMs, supports pause, resume, snapshot, fork, preview URLs, MCP connectivity, SDK/API control, Docker workloads, and self-hosting, while the hosted service adds pay-as-you-go agent sandboxes for teams.

open-sourceOpen Source