Verce

Provides a deployable MCP server on Vercel exposing tools and prompts via an HTTP endpoint for client integration.
  • typescript

0

GitHub Stars

typescript

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

You can run an MCP (Model-Consistency Protocol) server on Vercel to expose a scalable, modular interface for tools and prompts. This setup lets you deploy an MCP backend quickly and connect MCP clients via a simple deployment URL ending in /mcp, enabling practical tool invocations in your applications.

How to use

To use the MCP server from a client, point your client at the deployment URL followed by /mcp. The server serves a collection of tools you can call from your MCP client, handles prompts, and integrates with external APIs as configured in api/server.ts.

How to install

Prerequisites you should have before starting the MCP server on Vercel:

  • Node.js installed on your development machine
  • Access to a Vercel account for deployment
  • Optional: Fluid compute enabled on your Vercel project for efficient execution Follow these steps to get up and running from scratch.
1) Prepare your project
- Ensure you have an api/server.ts with your tools, prompts, and resources configured.
- Adjust vercel.json if you need to tweak deployment settings.

2) Install and initialize tooling
- Install the Vercel CLI if you do not have it yet.
- Login to Vercel and link your project to a Vercel deployment.

3) Deploy to Vercel
- Deploy the MCP template to obtain a live URL for your server.

4) Run locally (optional)
- Use vercel dev for local development to simulate the production environment.

5) Test the MCP endpoint
- After deployment, use your deployment URL with the /mcp path to reach the MCP server.

Additional notes and guidance

The setup includes example tools to help you get started. You can replace these with your own tools as needed. You may need to adjust the template settings for your specific tools, data sources, and API keys.

Notes for running on Vercel include ensuring Fluid compute is enabled for efficient execution and increasing the maximum duration in vercel.json if you are on a Pro or Enterprise plan.

A sample client is provided to try invocations against your live MCP server. You will deploy your server and then call tools through the client using your deployment URL.

Tools you can use with this MCP server

Two sample tools are included in the template to illustrate basic functionality and integration patterns. Replace them with your own tools as you expand your MCP setup.

Available tools

roll_dice

Rolls an N-sided die with a minimum of 2 sides, returning a random result for each invocation.

get_weather

Fetches current weather data for a specified location using latitude, longitude, and optional city name, integrating with a weather API.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational