Claude Desktop reads its servers from ~/Library/Application Support/Claude/claude_desktop_config.json. Of the 54 394 we track, 20 798 answer right now without any credentials, 8 428 sign you in through the browser and 3 298 want an API key you paste into the config. The blocks below are ready to paste — each is built from the address we actually reached, in the format this client expects.
It sits inside the application support folder, which Finder hides by default.
open ~/Library/Application\ Support/Claude/claude_desktop_config.json
For a local server it is the same JSON shape Cursor uses. A remote server does not go here: add it under Settings → Connectors → Add custom connector and paste its address.
Not just the conversation, the whole application: the config is read once at launch.
Settings → Connectors → Add custom connector, then paste this address
Browser Use →
https://api.browser-use.com/v3/mcp
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
Playwright Tools for MCP
Gives AI development tools Firebase-specific capabilities and expertise.
Help agents automatically write and test stories for your UI components.
Up-to-date docs for AI agents
MCP server for Chrome DevTools
Conversions across 221 color spaces, tested against cited sources: CSS strings, gamut, LUTs
Firecrawl, the context API for AI agents: search, scrape, interact with the web, plus paper search.
AI marketing agent and AI ad generator: 1178 tools, usable alone. No model markup on Starter and up.
Easily find and fix security issues in your applications leveraging Snyk platform capabilities.
Official TypeScript library for the Telnyx API
Open live web and mobile app sessions from an e2e project to inspect the app and try locators.
Written from how Claude Desktop reads its config, not from its release notes.
Editor with the agent built in. Takes stdio, streamable HTTP and SSE, and can carry an OAuth login for each of the three.
Autonomous agent living inside VS Code. Handles local processes and remote endpoints over streamable HTTP or SSE, but authorisation is on you — through headers or environment variables.
Google's command-line agent. Takes all three transports and carries a full OAuth flow for remote servers, including service-account impersonation.
Built into the JetBrains IDEs. Configured through the settings dialog rather than a file, and it can import a config you already wrote for another client.
Open-source terminal agent. Local and remote servers sit in the same mcp object, told apart by a type field, and tokens are kept outside the config.
Adds servers by command, so nothing to edit by hand. Handles both local processes and remote endpoints, including OAuth logins.
Config sits in the project folder, so servers can differ per repository — useful when one project needs database access and another must not have it.
Works through GitHub Copilot's agent mode. Like Cursor, the config is per workspace rather than global.
The only client here that uses TOML rather than JSON, so a config copied from elsewhere will not work as is.