Example MCP Server built on Next.js

Created By
MarkArmsronga year ago
MCP Server
Overview

what is MCP for Next.js?

MCP for Next.js is an example server built using the Next.js framework that implements the Model Context Protocol (MCP) for efficient data handling and processing.

how to use MCP for Next.js?

To use MCP for Next.js, update the app/mcp.ts file with your specific tools, prompts, and resources as per the MCP TypeScript SDK documentation. You can also run a sample client provided in script/test-client.mjs to test invocations.

key features of MCP for Next.js?

  • Built on the popular Next.js framework for easy deployment and scalability.
  • Integration with Redis for efficient data storage and retrieval.
  • Support for Fluid compute on Vercel for optimized performance.

use cases of MCP for Next.js?

  1. Building scalable web applications that require real-time data processing.
  2. Implementing server-side logic for complex data interactions.
  3. Creating a robust backend for applications using the Model Context Protocol.

FAQ from MCP for Next.js?

  • What is required to run MCP for Next.js?

You need to attach a Redis instance to your project and enable Fluid compute on Vercel for optimal performance.

  • Can I deploy MCP for Next.js on platforms other than Vercel?

While it is optimized for Vercel, you can deploy it on any platform that supports Node.js and Redis.

  • Is there a sample client available?

Yes! A sample client is included in the repository to help you test the server.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
MarkArmsrong
Star
0
Language
TypeScript
License
MIT license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago