Model README on the Python SDK's README

This commit is contained in:
Justin Spahr-Summers 2025-01-13 21:08:47 +00:00
commit 0790890bf3
No known key found for this signature in database
2 changed files with 334 additions and 95 deletions

433
README.md
View file

@ -1,6 +1,26 @@
# MCP TypeScript SDK ![NPM Version](https://img.shields.io/npm/v/%40modelcontextprotocol%2Fsdk)
# MCP TypeScript SDK ![NPM Version](https://img.shields.io/npm/v/%40modelcontextprotocol%2Fsdk) ![MIT licensed](https://img.shields.io/npm/l/%40modelcontextprotocol%2Fsdk)
TypeScript implementation of the [Model Context Protocol](https://modelcontextprotocol.io) (MCP), providing both client and server capabilities for integrating with LLM surfaces.
## Table of Contents
- [Overview](#overview)
- [Installation](#installation)
- [Quickstart](#quickstart)
- [What is MCP?](#what-is-mcp)
- [Core Concepts](#core-concepts)
- [Server](#server)
- [Resources](#resources)
- [Tools](#tools)
- [Prompts](#prompts)
- [Running Your Server](#running-your-server)
- [Development Mode](#development-mode)
- [Claude Desktop Integration](#claude-desktop-integration)
- [Direct Execution](#direct-execution)
- [Examples](#examples)
- [Echo Server](#echo-server)
- [SQLite Explorer](#sqlite-explorer)
- [Advanced Usage](#advanced-usage)
- [Low-Level Server](#low-level-server)
- [Writing MCP Clients](#writing-mcp-clients)
- [Server Capabilities](#server-capabilities)
## Overview
@ -19,158 +39,377 @@ npm install @modelcontextprotocol/sdk
## Quick Start
### Creating a Client
Let's create a simple MCP server that exposes a calculator tool and some data:
```typescript
import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";
import {
ListResourcesRequestSchema,
ReadResourceRequestSchema,
} from "@modelcontextprotocol/sdk/types.js";
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { z } from "zod";
const transport = new StdioClientTransport({
command: "path/to/server",
// Create an MCP server
const server = new McpServer({
name: "Demo",
version: "1.0.0"
});
const client = new Client({
name: "example-client",
version: "1.0.0",
}, {
capabilities: {}
});
await client.connect(transport);
// List available resources
const resources = await client.request(
{ method: "resources/list" },
ListResourcesResultSchema
// Add an addition tool
server.tool("add",
{ a: z.number(), b: z.number() },
async ({ a, b }) => ({
content: [{ type: "text", text: String(a + b) }]
})
);
// Read a specific resource
const resourceContent = await client.request(
{
method: "resources/read",
params: {
uri: "file:///example.txt"
}
},
ReadResourceResultSchema
// Add a dynamic greeting resource
server.resource(
"greeting",
"greeting://{name}",
async (uri, { name }) => ({
contents: [{
uri: uri.href,
text: `Hello, ${name}!`
}]
})
);
```
### Creating a Server
## What is MCP?
The SDK provides two ways to create a server: using the low-level `Server` class or the simplified `McpServer` class with an Express-style API.
The [Model Context Protocol (MCP)](https://modelcontextprotocol.io) lets you build servers that expose data and functionality to LLM applications in a secure, standardized way. Think of it like a web API, but specifically designed for LLM interactions. MCP servers can:
#### Using McpServer (Recommended)
- Expose data through **Resources** (think of these sort of like GET endpoints; they are used to load information into the LLM's context)
- Provide functionality through **Tools** (sort of like POST endpoints; they are used to execute code or otherwise produce a side effect)
- Define interaction patterns through **Prompts** (reusable templates for LLM interactions)
- And more!
## Core Concepts
### Server
The McpServer is your core interface to the MCP protocol. It handles connection management, protocol compliance, and message routing:
```typescript
import { McpServer } from "@modelcontextprotocol/sdk/server/index.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import { z } from "zod";
const server = new McpServer({
name: "example-server",
version: "1.0.0",
name: "My App",
version: "1.0.0"
});
```
// Define a simple tool with no parameters
server.tool("save", async () => {
return {
content: [{ type: "text", text: "Saved successfully." }]
};
});
### Resources
// Define a tool with parameters
server.tool("add", { a: z.number(), b: z.number() }, async ({ a, b }) => {
return {
content: [{ type: "text", text: String(a + b) }]
};
});
Resources are how you expose data to LLMs. They're similar to GET endpoints in a REST API - they provide data but shouldn't perform significant computation or have side effects:
// Define a static resource
```typescript
// Static resource
server.resource(
"welcome-message",
"file:///welcome.txt",
"config",
"config://app",
async (uri) => ({
contents: [{
uri: uri.href,
text: "Welcome to the server!"
text: "App configuration here"
}]
})
);
// Define a prompt with parameters
// Dynamic resource with parameters
server.resource(
"user-profile",
"users://{userId}/profile",
async (uri, { userId }) => ({
contents: [{
uri: uri.href,
text: `Profile data for user ${userId}`
}]
})
);
```
### Tools
Tools let LLMs take actions through your server. Unlike resources, tools are expected to perform computation and have side effects:
```typescript
// Simple tool with parameters
server.tool(
"calculate-bmi",
{
weightKg: z.number(),
heightM: z.number()
},
async ({ weightKg, heightM }) => ({
content: [{
type: "text",
text: String(weightKg / (heightM * heightM))
}]
})
);
// Async tool with external API call
server.tool(
"fetch-weather",
{ city: z.string() },
async ({ city }) => {
const response = await fetch(`https://api.weather.com/${city}`);
const data = await response.text();
return {
content: [{ type: "text", text: data }]
};
}
);
```
### Prompts
Prompts are reusable templates that help LLMs interact with your server effectively:
```typescript
server.prompt(
"greeting",
{ name: z.string(), language: z.string().optional() },
({ name, language }) => ({
"review-code",
{ code: z.string() },
({ code }) => ({
messages: [{
role: "assistant",
role: "user",
content: {
type: "text",
text: `${language === "es" ? "¡Hola" : "Hello"} ${name}!`
text: `Please review this code:\n\n${code}`
}
}]
})
);
const transport = new StdioServerTransport();
await server.connect(transport);
```
#### Using Server (Low-level API)
## Examples
### Echo Server
A simple server demonstrating resources, tools, and prompts:
```typescript
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { z } from "zod";
const server = new McpServer({
name: "Echo",
version: "1.0.0"
});
server.resource(
"echo",
"echo://{message}",
async (uri, { message }) => ({
contents: [{
uri: uri.href,
text: `Resource echo: ${message}`
}]
})
);
server.tool(
"echo",
{ message: z.string() },
async ({ message }) => ({
content: [{ type: "text", text: `Tool echo: ${message}` }]
})
);
server.prompt(
"echo",
{ message: z.string() },
({ message }) => ({
messages: [{
role: "user",
content: {
type: "text",
text: `Please process this message: ${message}`
}
}]
})
);
```
### SQLite Explorer
A more complex example showing database integration:
```typescript
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import sqlite3 from "sqlite3";
import { promisify } from "util";
import { z } from "zod";
const server = new McpServer({
name: "SQLite Explorer",
version: "1.0.0"
});
// Helper to create DB connection
const getDb = () => {
const db = new sqlite3.Database("database.db");
return {
all: promisify<string, any[]>(db.all.bind(db)),
close: promisify(db.close.bind(db))
};
};
server.resource(
"schema",
"schema://main",
async (uri) => {
const db = getDb();
try {
const tables = await db.all(
"SELECT sql FROM sqlite_master WHERE type='table'"
);
return {
contents: [{
uri: uri.href,
text: tables.map((t: {sql: string}) => t.sql).join("\n")
}]
};
} finally {
await db.close();
}
}
);
server.tool(
"query",
{ sql: z.string() },
async ({ sql }) => {
const db = getDb();
try {
const results = await db.all(sql);
return {
content: [{
type: "text",
text: JSON.stringify(results, null, 2)
}]
};
} catch (err: unknown) {
const error = err as Error;
return {
content: [{
type: "text",
text: `Error: ${error.message}`
}],
isError: true
};
} finally {
await db.close();
}
}
);
```
## Advanced Usage
### Low-Level Server
For more control, you can use the low-level Server class directly:
```typescript
import { Server } from "@modelcontextprotocol/sdk/server/index.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import {
ListResourcesRequestSchema,
ReadResourceRequestSchema,
ListPromptsRequestSchema,
GetPromptRequestSchema
} from "@modelcontextprotocol/sdk/types.js";
const server = new Server({
name: "example-server",
version: "1.0.0",
}, {
capabilities: {
resources: {}
const server = new Server(
{
name: "example-server",
version: "1.0.0"
},
{
capabilities: {
prompts: {}
}
}
});
);
server.setRequestHandler(ListResourcesRequestSchema, async () => {
server.setRequestHandler(ListPromptsRequestSchema, async () => {
return {
resources: [
{
uri: "file:///example.txt",
name: "Example Resource",
},
],
prompts: [{
name: "example-prompt",
description: "An example prompt template",
arguments: [{
name: "arg1",
description: "Example argument",
required: true
}]
}]
};
});
server.setRequestHandler(ReadResourceRequestSchema, async (request) => {
if (request.params.uri === "file:///example.txt") {
return {
contents: [
{
uri: "file:///example.txt",
mimeType: "text/plain",
text: "This is the content of the example resource.",
},
],
};
} else {
throw new Error("Resource not found");
server.setRequestHandler(GetPromptRequestSchema, async (request) => {
if (request.params.name !== "example-prompt") {
throw new Error("Unknown prompt");
}
return {
description: "Example prompt",
messages: [{
role: "user",
content: {
type: "text",
text: "Example prompt text"
}
}]
};
});
const transport = new StdioServerTransport();
await server.connect(transport);
```
### Writing MCP Clients
The SDK provides a high-level client interface:
```typescript
import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";
const transport = new StdioClientTransport({
command: "node",
args: ["server.js"]
});
const client = new Client(
{
name: "example-client",
version: "1.0.0"
},
{
capabilities: {
prompts: {},
resources: {},
tools: {}
}
}
);
await client.connect(transport);
// List prompts
const prompts = await client.listPrompts();
// Get a prompt
const prompt = await client.getPrompt("example-prompt", {
arg1: "value"
});
// List resources
const resources = await client.listResources();
// Read a resource
const resource = await client.readResource("file:///example.txt");
// Call a tool
const result = await client.callTool("example-tool", {
arg1: "value"
});
```
## Documentation
- [Model Context Protocol documentation](https://modelcontextprotocol.io)

4
package-lock.json generated
View file

@ -1,12 +1,12 @@
{
"name": "@modelcontextprotocol/sdk",
"version": "1.1.0",
"version": "1.1.1",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "@modelcontextprotocol/sdk",
"version": "1.1.0",
"version": "1.1.1",
"license": "MIT",
"dependencies": {
"content-type": "^1.0.5",