Remote MCP vs Local MCP

MCP servers come in two varieties based on where they run: Local MCP, which runs on your computer, and Remote MCP, which runs on a server somewhere on the internet. I will use Figma’s Native MCP to make this concrete for beginners.

Start With a Simple Question: “Where Does the MCP Server Live?”

When you start learning about MCP, a natural question arises:

“Does the MCP server run on my computer, or does it run on Figma’s servers?”

Your answer to that question is exactly the difference between Local MCP and Remote MCP.

The location where an MCP server runs determines how it connects, how secure it is, and how much setup it requires.

Local MCP: Runs on Your Computer

Local MCP is an approach where the MCP server starts up on your local machine.

The AI app (the Host) and the MCP server communicate via standard I/O (stdio) — a mechanism where programs exchange text by reading from and writing to their input and output streams. Both processes run on the same machine.

How Local MCP Works

Your Computer
┌─────────────────────────────────────────┐
│  Claude Desktop (AI Host)               │
│        ↕ stdio (inter-process comm.)    │
│  File System MCP Server                 │
│        ↕                               │
│  📁 Your Local Files                    │
└─────────────────────────────────────────┘
Internet connection: Not required

Concrete Examples of Local MCP Servers

MCP Server	What It Does
File System MCP	Read and write files on your computer
Git MCP	Operate on local Git repositories
SQLite MCP	Query a local database
Browser MCP	Control a locally running browser

Local MCP Characteristics

Item	Details
Where it runs	Your computer
Communication	stdio (standard I/O)
Internet required	No
Security	High (data never leaves your machine)
Setup effort	Moderate to high (installation required)
Getting started	Moderate (may require command-line knowledge)

Remote MCP: Runs on a Server on the Internet

Remote MCP is an approach where the MCP server runs on the service provider’s servers. Nothing needs to be installed on your machine — the AI app communicates with the MCP server over the internet.

The communication uses HTTP + SSE (Server-Sent Events). SSE is a mechanism that lets a server push data to a client continuously in real time.

How Remote MCP Works

Your Computer                    The Internet
┌─────────────────┐              ┌──────────────────────┐
│ Claude Desktop  │ ←─HTTP/SSE─→ │ Figma MCP Server     │
│ (AI Host)       │              │ (operated by Figma)  │
└─────────────────┘              │   ↕ OAuth auth        │
                                 │  📐 Figma data        │
                                 └──────────────────────┘
Internet connection: Required

Understanding Remote MCP Through Figma Native MCP

In 2025, Figma released Figma Native MCP — an official remote MCP server. It is one of the clearest real-world examples of remote MCP.

What Is Figma Native MCP?

Figma is a UI design tool. Designers use it to create buttons, layouts, and icons.

Previously, if an AI needed to work with Figma data, a developer had to build a custom integration from scratch. Figma Native MCP changes that:

AI apps like Claude Desktop can access Figma data by setting a single URL — no custom code needed.

The Setup Flow (Beginner-Friendly)

Open Claude Desktop’s settings and enter the Figma MCP server URL
Authorize access through Figma’s OAuth login
Done! The AI can now read and interact with Figma files and components

Nothing needs to be installed on your computer.

MCP Skills (Capabilities): Concrete Real-World Examples With Figma

The features that an MCP server provides are called Skills — or in MCP terminology, capabilities. There are three types. I will explain each using Figma as a concrete example.

Tools: Operations the AI Can “Execute”

Tools are functions that the AI invokes to do something. These are operations that change state — creating, updating, or deleting things.

Figma Examples

Tool Name	What Happens	How You’d Use It
`create_frame`	A new frame is created in Figma	”Create a frame for the login screen”
`update_node`	An existing element (text, color, etc.) is modified	”Change this button’s background color to blue”
`set_variable`	A design token (variable) is updated	”Set the primary color to #3B82F6”

Everyday analogy: “Tools are like telling a robot to ‘put something on the shelf.’ The physical state of the world changes.”

Important: Because Tools “do something,” a confirmation screen may appear before they execute.

Resources: Data the AI Can “Read”

Resources provide read-only data. Nothing is changed or created.

Figma Examples

Resource	What You Get	How You’d Use It
Figma file list	Your projects and files	”What projects do I have?”
Component info	Specs for buttons, cards, and other components	”Show me the button design spec”
Frame structure	Layout and layer hierarchy of a screen	”Describe the structure of the login screen”

Everyday analogy: “Resources are like telling a robot to ‘look at the shelf.’ Nothing moves.”

Important: Resources are “look but don’t touch” — they are safer than Tools.

Prompts: Saving Repeated Tasks as “One-Click Templates”

Prompts are reusable templates for common questions or instructions, stored server-side.

Figma Examples

Prompt Name	What It Does
`design_review`	Automatically runs: “Review this Figma design for accessibility”
`generate_component_spec`	Automatically runs: “Generate an implementation spec for this component”

Everyday analogy: “Prompts are like saving your usual lunch order as a favorite. One tap and the same instruction runs.”

More Remote MCP Examples Beyond Figma

Many services beyond Figma provide remote MCP servers.

Service	Tools Examples	Resources Examples
GitHub	`create_issue`, `merge_pr`	Repository structure, file contents
Slack	`send_message`, `create_channel`	Channel history, member list
Notion	`create_page`, `update_block`	Document content, databases

Side-by-Side Comparison

Comparison	Local MCP	Remote MCP
Where it runs	Your computer	Provider’s server on the internet
Communication	stdio	HTTP + SSE
Internet not needed	✅	❌
No installation needed	❌	✅
Good for private data	✅ (never leaves your machine)	⚠️ (sent to the server)
Always up to date	❌ (manual updates)	✅ (provider manages updates)
Representative examples	File system, Git, SQLite	Figma, GitHub, Slack

Which Should I Choose?

Local MCP is a better fit when:

I want to access files or private data on my computer
I am working in an environment without internet access
I do not want sensitive data sent to an external server

Remote MCP is a better fit when:

I want to access data from a web service like Figma or Slack
I want a simple setup with minimal configuration
I want to always have the latest features (the provider handles updates)

I can use both simultaneously. For example, in Claude Desktop I can configure the File System MCP (local) alongside Figma Native MCP (remote). The AI can then work with both local files and Figma data in the same conversation.

Summary

Local MCP: Runs on your computer, communicates via stdio. Best for local files, databases, and private resources
Remote MCP: Runs on a server on the internet, communicates via HTTP + SSE. Best for web services and APIs
Figma Native MCP: A prime example of remote MCP — set a URL, authenticate with OAuth, and it’s ready
Skills (Tools / Resources / Prompts): The three categories of functionality an MCP server provides — execute, read, and template

Next Steps

What is MCP? — Return to the core concepts
Why MCP? — Understand the M×N integration problem
MCP Architecture — Explore the Host, Client, and Server structure in depth
MCP Capabilities — Detailed specs for Tools, Resources, and Prompts

Frequently Asked Questions

Q: Do I need a paid Figma plan to use Figma Native MCP?

A: Basic functionality is available with a Figma account. Some advanced features may depend on your subscription tier. Check Figma’s official documentation for the latest details.

Q: Can I use Local MCP and Remote MCP at the same time?

A: Yes. In Claude Desktop’s settings, I can register both local MCP servers and remote MCP servers simultaneously. The AI can access resources from both within the same conversation.

Q: Can I build my own remote MCP server?

A: Yes. Implementing a server that supports HTTP + SSE and follows the MCP protocol is all that is required. The official MCP documentation includes examples hosted on Cloudflare Workers and Vercel.

References

Link to this page (Japanese): リモートMCPとローカルMCP