Tony Lewis

We ran into a problem a few weeks ago that none of our tools could solve. It wasn't a technical problem — the code was fine, the infra was fine. We just needed someone to go do a thing on a website. Sign up, click around, grab some information, paste it into a form. Repeat a bunch of times.

AI couldn't do it. The sites had captchas, email verification, multi-step flows. We tried browser automation and it broke immediately. We needed a person.

So we thought: what if our AI agent could just hire one?

Most Obsidian MCP servers give you six tools: read a file, write a file, search, list, patch, delete. Basic CRUD over Markdown. That's table stakes.

This one does things the others can't. Your AI sees images in your vault — diagrams, whiteboard photos, screenshots — through actual vision, not file paths. It traverses your wikilink graph and finds orphaned notes nothing links to. It edits a specific section of a document by heading or block reference without overwriting the rest. It lists every open task across your entire vault. It runs Obsidian commands directly from the command palette.

It works with Claude Desktop, ChatGPT, Cursor, Windsurf, or any MCP client. No npm install, no local server, no JSON config. One remote URL and your AI has the tools.

Directories like Glama index over 20,000 MCP servers. Most of them are weekend projects. Some of them are brilliant. A surprising number of them just don't work.

We've been running MCPBundles for over a year — a platform where teams connect their AI agents to production APIs. We've tested, wrapped, and maintained MCP servers for hundreds of services. This guide is what we've learned about which ones are worth your time.

Claude Code has built-in MCP (Model Context Protocol) support that lets your AI coding agent connect to external services — databases, APIs, SaaS platforms — directly from the terminal. This guide covers everything: the native CLI commands, configuration options, transport types, and how to scale beyond a handful of servers.

Here's the thing nobody tells you about Cursor's agent mode: it's brilliant at working with code and completely blind to everything your code talks to.

Last week we were debugging a webhook handler. Cursor had the code open, understood the control flow, spotted a race condition in the retry logic. Genuinely impressive. Then we needed to know whether the bug was actually hitting production — were customers seeing duplicate charges? The agent that just did 15 minutes of sophisticated code analysis couldn't answer a basic factual question about our own Stripe data.

So we opened a browser tab, logged into Stripe, searched for the customer, scrolled through PaymentIntents, compared timestamps manually, went back to Cursor, and typed what we found. The AI had all the context and none of the data.

We got tired of being the copy-paste bridge between our IDE and our dashboards.

Glama indexes 20,000+ MCP servers. Smithery has 8,000+. mcp.so has 6,000+. There's no shortage of servers to find.

The problem is everything that happens after you find one.

You pick a promising-looking Stripe MCP server from a directory. Now you need to clone the repo, install its dependencies (hope they don't conflict with yours), figure out whether it uses env or args for the API key, add your key to a JSON config file in plaintext, start the process, and configure your AI client to talk to localhost:3000. If you're lucky, it works. If the repo hasn't been updated in three months, it probably doesn't.

Repeat that for every service you want to connect. We got to five local MCP server processes before we gave up and built something better.

If you've set up an MCP server before, you know the drill. Clone a repo. Install dependencies. Add your API key to a JSON config file. Start the process. Configure your AI client to connect to localhost:3000. Repeat for every service you want to use.

It works. Until it doesn't. The process crashes silently. Your laptop sleeps and the server dies. You upgrade Node and the dependencies break. A teammate wants access and you're sharing API keys over Slack. You add a third service and now you're managing three server processes, three config files, and three sets of credentials in plaintext on your machine.

Local MCP servers are fine for trying things out. For daily use across a team, you need hosting.

Yes, Windsurf supports MCP. Cascade — Windsurf's AI agent — can connect to external MCP servers to access databases, APIs, and SaaS platforms directly from your IDE. This guide covers setup, configuration, known limitations, and how to work around the 100-tool cap.

Every AI platform supports MCP tools. But what happens when the tool you need doesn't exist yet? Maybe you're working with an internal API, a niche SaaS, or a service that nobody has wrapped in MCP. Until now, you'd write a custom server.

Now your AI can do it itself.

MCPBundles has always worked as an MCP server. You add it to Claude Desktop, Cursor, ChatGPT, or any MCP-compatible client, and your AI gets access to Stripe, HubSpot, Postgres, PostHog, Gmail, and every other service you've connected — with real credentials, real permissions, and real data.

The MCPBundles CLI is an alternative way to access those same tools. Instead of configuring MCPBundles as a remote MCP server in your client, you install a command-line tool and authenticate with an API key. The AI agent discovers and calls your tools through shell commands — the same 10,000+ tools, the same credentials, the same workspace permissions.

pip install mcpbundles