WhatsApp MCP Platform
Provides a Model Context Protocol server for WhatsApp, enabling session management, webhook normalization, and tenant-based message operations through a public API and private control plane.
README
WhatsApp MCP Platform
A Bun-workspace monorepo for the three independently deployed applications defined by ADR 0002:
apps/web: the Next.js product UI on Vercelapps/api: the public Cloudflare API Workerapps/provider-control: the private Cloudflare Worker reachable only through an API service binding
Shared modules have explicit subpath exports and no catch-all barrel:
packages/domain: pure domain rulespackages/contracts: product and MCP schemaspackages/db: database configuration, migrations, and tenant repositoriespackages/wasender: separate session, control, and webhook-normalization boundaries
Local verification
bun install --frozen-lockfile
bun run format:check
bun run lint
bun run typecheck
bun run validate:infra
bun run test
bun run build
bun run manifests:validate
bun run infra:validate
Run a deployable locally with Turbo filtering, for example:
bun run dev --filter=@whatsapp-mcp/web
Production and test Effect roots are separate modules. Runtime configuration cannot select a test Layer, and the production build inspection fails if a test Layer marker enters a deployable artifact.
See deployment configuration and the deployment runbook.
The OpenTofu compute topology in infra/compute uses separate state and
authority for development, preview, and production. It declares the Vercel web
project, the public API Worker custom-domain route, and the private
provider-control Worker service binding.
Sandcastle
Sandcastle runs issue agents in isolated Docker worktrees. After authenticating Docker, GitHub CLI, and Codex:
bun run sandcastle:build-image
bun run sandcastle
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.