MCP TypeScript SDK
Official TypeScript/JavaScript SDK for building MCP servers and clients — the Node.js foundation for the Model Context Protocol.
MCP TypeScript SDK
The MCP TypeScript SDK is the official reference implementation of the Model Context Protocol for Node.js and browser environments. Build MCP servers (tools, resources, prompts) and MCP clients with full type safety, Zod-powered schema validation, and transport adapters for stdio, HTTP SSE, and WebSocket.
Key Features
- Full protocol coverage: implement servers exposing tools, resources, and prompt templates; build clients that consume them
- Transport agnostic: stdio (for local process servers), HTTP+SSE (for network servers), and in-process for testing
- Zod integration: define tool input schemas with Zod; automatic JSON Schema generation and runtime validation
- TypeScript-first: complete type inference for tool inputs/outputs; no
anyrequired - OAuth 2.1 support: built-in token management for authenticated remote MCP servers
- Streaming: server-sent events transport supports incremental resource and tool responses
Quick Start
npm install @modelcontextprotocol/sdk
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import { z } from "zod";
const server = new McpServer({ name: "my-server", version: "1.0.0" });
server.tool("add", { a: z.number(), b: z.number() }, async ({ a, b }) => ({
content: [{ type: "text", text: `${a + b}` }],
}));
await server.connect(new StdioServerTransport());
npx ai-supply add mcp-typescript-sdk
Curated mirror of the open-source MCP TypeScript SDK (Apache-2.0). Get it from the source.
Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.
Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).
The same gate an agent runs before installing (POST /api/v1/trust/mcp-typescript-sdk/check). Click a policy:
Consume MCP TypeScript SDK programmatically. Authenticate with an API key or session — see Authorize an agent.
# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/mcp-typescript-sdk
# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/mcp-typescript-sdk/check \
-H "Content-Type: application/json" \
-d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'
# CLI
npx ai-supply add mcp-typescript-sdk
# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/mcp-typescript-sdk/install \
-H "Authorization: Bearer $AIM_KEY"
# MCP tool
install_listing({ "slug": "mcp-typescript-sdk" })OpenAPI spec →Curated mirror — latest upstream source. See the repository for tagged releases.