MCP

In Add GitHub OAuth to a FastMCP Server you delegated login to GitHub. That is a good fit when your users already have GitHub accounts, but it ties your server to one social provider. This tutorial uses Clerk instead: a full authentication platform where you own the user directory. Clerk gives you email/password, magic links, social logins, and MFA behind a single OAuth authorization server, and FastMCP’s ClerkProvider plugs that server into your MCP server with a few lines of configuration. ...

Sometimes the MCP server you want your team to use already exists — published to a registry, a GitHub repo, or a container image by someone else. You do not need to fork it or vendor its source into your plugin. A Claude Code plugin can be pure configuration: a .mcp.json that tells Claude Code how to launch that external server over stdio, wrapped in a manifest and a marketplace so a teammate installs it with one command. ...

A Claude Code plugin can ship an MCP server the same way it ships a command or a hook: drop a .mcp.json at the plugin root, and Claude Code starts the server for anyone who installs the plugin. The user runs no pip install, edits no config, and copies no path. They install the plugin, and the server’s tools appear. The trick that makes this painless is launching the server with uv run --script against a file that declares its own dependencies inline (PEP 723). The consumer needs only uv on their PATH; uv builds an ephemeral environment with the right packages on first run. No committed virtualenv, nothing to install ahead of time. ...

Higgsfield ships a bundled video-explainer workflow through its MCP server: hand it a script and it produces a narrated, animated video by generating one 10-second clip per line, voicing each line, and stitching the result into a single MP4. This guide runs that workflow from Claude Code, using a short made-up script so you can see exactly how a few lines of text become finished clips. Claude Code is a good fit here because the whole flow is text-driven. Every visual is generated from a written style description and per-block prompts, so there are no local files to upload — the terminal client never needs to render an upload widget. You paste a script, answer a few setup questions, and Claude Code orchestrates the Higgsfield tools for you. ...

Higgsfield exposes its image and video generation as an MCP server, so you can produce short-form video by chatting with an MCP client instead of clicking around a web app or wiring up an API. This guide uses its Shorts Studio flow: you hand it one source video, pick a visual style, and it returns a set of vertical, AI-restyled clips sized for YouTube Shorts. There is no code to write. The whole workflow is a conversation with an assistant that has the Higgsfield connector enabled; behind each message, the assistant calls a Higgsfield MCP tool. This article shows what to say, which tool runs, and what comes back, grounded in the live server. ...

The earlier MCP articles built servers that expose tools and a client that calls those tools by hand: you name the tool, you supply the arguments. An agent is the piece that makes those decisions for you. Given a question and a set of MCP tools, it asks a model which tool to call, runs it, feeds the result back, and repeats until the model has an answer. This article builds that agent with the Anthropic Python SDK and FastMCP, on macOS with uv, make, and pytest. The loop is the standard Anthropic tool-use loop; the only twist is that the tools come from an MCP server instead of being defined inline. ...

As an MCP deployment grows, one giant server file stops scaling. FastMCP offers two ways to build bigger servers from smaller ones: Composition mounts independently-developed sub-servers into one gateway, so a team can own a math server and another own a text server, and a client sees them as one. Proxying puts a FastMCP server in front of an existing MCP server (even a remote one), forwarding every request to it. That lets you add TLS, auth, or rate limiting in front of a server you do not control, or expose a remote server under your own address. This article builds both: a gateway composed from two sub-servers, and a proxy that fronts an existing HTTP server. The stack is Mac-native: uv and make. ...

Most tools take their inputs up front and return an answer. Two MCP capabilities turn that around and let a tool ask the client for something mid-run: Elicitation asks the user for structured input, so a tool can request a missing value or a confirmation instead of failing. Sampling asks the client’s LLM for a completion, so a tool can use the model the client already has rather than calling one itself. Both are server-to-client requests: the tool pauses, the client answers, and the tool continues. This article builds a FastMCP server that uses each, and a client that answers them. The final tool chains the two: it elicits who a bio is for, then samples the model to write it. The stack is Mac-native: uv and make. ...

A tool that returns in a few milliseconds needs no ceremony. A tool that runs for several seconds does: without feedback, the client looks frozen, and a user (or a model) cannot tell a slow success from a hang. MCP solves this with progress notifications and log messages that stream back to the client while the tool is still running. This article builds a FastMCP tool that reports progress as it works, and a client that renders a live progress bar from those notifications. ...

The tools in the earlier articles computed their answers locally. Most useful tools instead reach out to an external service: a weather API, a payments provider, an internal microservice. That introduces three problems a naive httpx.get ignores: where the API key lives, what happens when the call is slow, and how a failure reaches the user. This article builds a FastMCP tool that calls a real HTTP API and handles all three, the macOS way. ...