Stash / Blog · June 2026 · 5 min read

What Is MCP for Claude? Model Context Protocol Explained Simply

You've seen "MCP" mentioned in Claude settings, on developer forums, and in AI tooling discussions. What actually is it?

Short version: MCP lets Claude reach out to external tools and services during a conversation. Instead of Claude only knowing what's in the chat window, it can query a database, read a file, call an API — and use those results to answer better.

The problem MCP solves

Without MCP, Claude is isolated. Every conversation starts blank. Claude knows its training data, and it knows what you type into the chat. That's it.

That's fine for writing assistance and general reasoning. It breaks down when you need Claude to work with your specific data: your clients, your notes, your database, your documents.

The old solution was copy-pasting: you'd copy relevant context into the chat. This is slow, hits the context window limit fast, and means Claude only knows what you remembered to paste.

MCP is a better solution: a standard protocol that lets Claude call external services mid-conversation, get structured responses back, and use that data in its answers.

How MCP actually works

An MCP server is a small service that exposes "tools" — callable endpoints with defined inputs and outputs. Claude can see what tools are available and decide when to call them.

When Claude needs information from an MCP server, it makes a tool call. The server returns a structured result. Claude incorporates it into its response.

From your side, it looks seamless:

You: What do I know about the Acme project?

Claude: [internally: calls search("Acme", collection="projects") on your Stash MCP server]

Claude: Based on your records, Acme Corp is in the retail sector. The current project
        is a Q3 strategy review with a July deadline. Last decision: Option B on pricing.
        Would you like me to draft the exec summary?

Claude looked up your data. You didn't have to paste anything.

Two types of MCP: local and remote

Local MCP servers

Run on your machine. Claude Desktop connects to them via a config file. Good for file system access, local databases, developer tools. Requires some setup and doesn't work on mobile or other devices.

Remote MCP servers (hosted)

Run on a server. You connect by pasting a URL into Claude settings. Works from any device, any Claude session. No local setup needed.

For most non-developers, hosted (remote) MCP servers are the practical choice. You get the capabilities without managing a local service.

What you can do with MCP

The ecosystem is growing fast. Common categories:

CategoryWhat it enablesExample
Memory / notesStore and retrieve your recordsStash — structured notes and lists
File accessRead and write local filesFilesystem MCP
DatabasesQuery databases of any kinddatabase connectors
Web toolsSearch, fetch pages, scrapeBrave Search MCP
Dev toolsRun code, manage reposGitHub MCP
CommunicationSend emails, check calendarGmail MCP, Calendar MCP

How to add an MCP server to Claude

In Claude Desktop:

  1. Go to Settings → Developer → Edit Config
  2. Add the MCP server entry (the server's docs will give you the exact config)
  3. Restart Claude Desktop

In Claude.ai (web, remote MCP):

  1. Go to Settings → Integrations
  2. Paste the connector URL
  3. Authorize the connection

For hosted MCP servers like Stash, you just paste a URL. No config file editing needed.

Token-light matters. Not all MCP servers are created equal. A server that dumps thousands of tokens per call will slow Claude down and increase costs. Good MCP servers — like Stash — return only what Claude needs: search results, not the whole database.

Getting started: the best first MCP

If you're new to MCP, start with a memory/notes server. It has an immediate, obvious payoff: you stop re-briefing Claude every session.

Stash is a hosted MCP that stores structured records. Add it to Claude in 30 seconds:

  1. Go to stashlite.com
  2. Connect with Google to get your personal connector URL
  3. Paste it into Claude Desktop or claude.ai settings
  4. Ask Claude: context() to confirm the connection works

The free tier includes 2,500 records and 50 queries per month. Enough to get a feel for what structured MCP memory changes about your Claude workflow.

Try MCP Memory for Claude

Stash: hosted, free to start, connects in 30 seconds.

Add to Claude →

Further reading