digital-mgmt-mcp

digital-mgmt-mcp

MCP server for Akij Resource Digital Management team providing KPI summaries and utility tools (time, echo, calculation) over Streamable HTTP, deployable to Vercel.

Category
Visit Server

README

digital-mgmt-mcp

A Model Context Protocol (MCP) server for the Akij Resource Digital Management team, built with TypeScript and the official MCP SDK. It uses the Streamable HTTP transport so it can run as a Vercel serverless function (and also locally over stdio).

Tools

Tool Description
get_time Current UTC time / ISO timestamp / epoch ms
echo Echo a message back
calculate Safe arithmetic evaluation (+ - * / % ( ))
digital_kpi_summary FY2026 Digital Management KPI summary (real DWH figures + sample marketing data), with optional SBU filter

Project layout

api/mcp.ts        Vercel entry — Express app + Streamable HTTP transport (deployed function)
src/tools.ts      Tool definitions (shared)
src/server.ts     Local HTTP dev server (npm run dev)
src/stdio.ts      Local stdio runner (npm run stdio)
vercel.json       Vercel build/function config

Local development

npm install
npm run dev        # HTTP server on http://localhost:3000/mcp
# or
npm run stdio      # stdio transport (for local MCP clients)

Deploy to Vercel

  1. Install the Vercel CLI: npm i -g vercel
  2. vercel (link the project) then vercel --prod
  3. Your MCP endpoint will be https://<project>.vercel.app/api/mcp

Push to GitHub

git init
git add .
git commit -m "init: digital management MCP server"
git branch -M main
gh repo create digital-mgmt-mcp --public --source=. --push

Connect to the MCP

Add it as a remote MCP server in your client (e.g. opencode.json):

{
  "mcp": {
    "digital-mgmt-mcp": {
      "type": "remote",
      "url": "https://<project>.vercel.app/api/mcp",
      "enabled": true
    }
  }
}

Adding a tool

Register new tools in src/tools.ts with a zod schema for typed arguments:

server.tool(
  "my_tool",
  "What this tool does.",
  { input: z.string().describe("Description of the input") },
  async ({ input }) => ({
    content: [{ type: "text", text: `You said: ${input}` }],
  })
);

Secrets (API keys, DB credentials) belong in Vercel environment variables — never commit them.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured