¿Qué es el
Model Context Protocol?
If you've seen Claude do things like search the web, read your files, or log a transaction in your finance tracker — that's MCP at work. Model Context Protocol is the open standard that makes it possible for AI assistants to connect to external tools and services in a structured, secure way.
The problem MCP solves
Large language models are trained on static data. Without external connections, they can't check today's weather, read your latest emails, or write to a database. Developers have long worked around this with ad-hoc integrations — custom function calls, bespoke plugins, one-off APIs. Each integration was different, hard to reuse, and only worked with one model.
MCP standardizes the interface. Instead of building a custom integration for each AI model, you build one MCP server and any MCP-compatible client can use it.
How MCP works
MCP defines a client-server protocol. The MCP client is the AI assistant (like Claude). The MCP server is an external service that exposes tools and resources. The two communicate over a defined protocol — either via standard input/output (for local servers) or HTTP with Server-Sent Events (for remote servers).
Tools
Tools are callable functions exposed by the MCP server. Claude can call them on your behalf. A tool has a name, a description (which Claude reads to understand what it does), and a JSON Schema for its input parameters. For example:
add-transaction— logs a new transaction to your finance trackerweb_search— searches the web and returns resultsread_file— reads a file from your local filesystemcreate_issue— creates a GitHub issue
Resources
Resources are data that the MCP server exposes for Claude to read — like the contents of a file, a database record, or in Kachink's case, an interactive dashboard rendered as an HTML page inside the chat.
Authentication
Remote MCP servers (accessed over HTTP) use OAuth 2.0 for authentication. When you connect Kachink to Claude, you're redirected to Google OAuth to prove your identity. Claude then holds an access token that authorizes it to call Kachink's tools on your behalf.
MCP in practice: example servers
The MCP ecosystem has grown rapidly since Anthropic open-sourced the spec in late 2024. Here are some categories of MCP servers people use today:
- Filesystem — read, write, and search files on your local machine
- GitHub — create issues, review PRs, search repositories
- Databases — query PostgreSQL, SQLite, or other databases
- Productivity — create calendar events, search emails, manage tasks
- Finance — log transactions, query spending, manage budgets (Kachink)
- Web — search the web, fetch pages, extract structured data
How Kachink uses MCP
Kachink is a personal finance tracker built entirely as a remote MCP server. When
you add https://kachink.app/mcp to Claude, Claude gains access to
these tools:
add-transaction— log an expense or income entryget-transactions— retrieve transactions for a given monthget-month-data— fetch aggregated monthly data for the dashboardadd-recurring— set up a recurring monthly transactionedit-transaction— update an existing transactiondelete-transaction— remove a transaction
Claude reads the tool descriptions, understands when to use each one, and calls
them based on what you ask in natural language. When you say "log $47 for lunch",
Claude calls add-transaction with the right parameters — no form,
no UI, no context switching.
Kachink also uses MCP Apps — a feature of the MCP protocol that lets servers return interactive HTML UIs. When you ask Claude to "open the dashboard", Kachink returns a full rendered dashboard as an MCP App that appears inside the chat interface.
Getting started with MCP
To use any MCP server with Claude, open Claude's settings, navigate to Integrations, and add the server URL. For remote servers like Kachink, you'll be prompted to authenticate.
If you want to build an MCP server, Anthropic maintains official SDKs
for TypeScript and Python. The TypeScript SDK is published as
@modelcontextprotocol/sdk on npm.
Ready to try an MCP server? Agregar Kachink a Claude and log your first transaction — the whole setup takes under a minute.
Preguntas comunes sobre MCP
MCP (Model Context Protocol) es un estándar abierto de Anthropic que permite a asistentes de IA como Claude conectarse con herramientas, APIs y fuentes de datos externas. En lugar de limitarse a datos de entrenamiento, Claude puede usar servidores MCP para realizar acciones en el mundo real.
MCP fue creado por Anthropic y publicado como código abierto en noviembre de 2024. La especificación y los SDKs están disponibles en github.com/modelcontextprotocol.
Claude.ai soporta servidores MCP remotos a través de la página de ajustes de Integraciones. Otros clientes incluyen Claude Desktop, Cursor, Windsurf y cualquier aplicación construida con el SDK de MCP. Los servidores remotos (accesibles vía HTTPS) funcionan con Claude.ai directamente.
Kachink escribe y almacena sus datos de forma persistente en una base de datos Cloudflare D1, con aislamiento por usuario y autenticación Google OAuth. También sirve un panel de control interactivo como MCP App. Vea el tutorial de configuración →
Vea MCP en acción con Kachink
Agregue Kachink como su primer servidor MCP y experimente cómo el lenguaje natural se convierte en llamadas estructuradas a herramientas — sin que usted haga nada del trabajo.
https://kachink.app/mcp