Getting Started

This guide will help you get up and running quickly—whether you choose our hosted cloud offering or run ContextMesh on your own infrastructure.

Prerequisites & System Requirements

Before you begin, make sure you have the following in place:

Requirement
Minimum Version / Notes

Operating System

macOS 10.15+, Linux (x86_64 or ARM64), or Windows 10+ (WSL recommended)

CPU & RAM

≥ 2 CPU cores, ≥ 4 GB RAM (8 GB+ recommended for heavy workloads)

Node.js

≥ 14.x (for CLI & SDK generation)

Python

≥ 3.8 (for Python SDK & scripts)

Docker

≥ 20.x (only required for self-hosted deployments)

Git

≥ 2.x (to clone repositories and sync manifests)

Network

Outbound HTTPS on ports 443 (to reach MCP endpoints or ContextMesh Cloud)

Browser

Chrome, Firefox, Edge, or Safari (latest stable releases)

Tip: If you plan to build or extend manifests using our CLI, you’ll also need your preferred code editor (VS Code, WebStorm, etc.) with JSON/TypeScript support enabled.

Hosted vs. Self-Hosted Options

ContextMesh supports two deployment modes. Choose the one that best fits your security, compliance, and scalability needs.

1. Hosted (Cloud)

Our managed service lets you focus on building MCP manifests—no infrastructure to maintain.

  • Zero Ops: We handle provisioning, scaling, monitoring, and upgrades.

  • Instant Access: Spin up workspaces in seconds and share public demos via URL.

  • Built-in Security: ISO-certified hosting, encrypted-at-rest and in-transit, SOC-2 compliant.

  • Pay-as-you-go: Only pay for active manifests and API usage.

  • Integrations: Native support for GitHub SSO, Slack notifications, and Webhooks.

Getting started with Hosted

  1. Sign up at app.contextmesh.com.

  2. Create your first workspace and import a manifest.json.

  3. Use the web IDE to drag & drop blocks, then click Publish → Export Manifest.

2. Self-Hosted (On-Prem or VPC)

Run ContextMesh inside your own network for full control and data residency.

  • Custom Networking: Deploy behind your firewall or inside a private VPC.

  • Data Residency: Keep manifests, logs, and metrics on-premises or in your isolated cloud.

  • Version Control: Pin to a specific ContextMesh release and upgrade on your schedule.

  • Extensibility: Install custom plug-ins, connect to internal toolchains, and run private tooling.

Getting started with Self-Hosted

  1. Clone the repo:

    git clone https://github.com/contextmesh/contextmesh.git

  2. Launch the stack with Docker Compose (or Helm for Kubernetes):

    docker-compose up -d

  3. Configure environment variables in .env:

    MCP_ENDPOINT=https://your.local.host:8443
ADMIN_API_KEY=your_admin_key

  4. Point your CLI or SDKs at MCP_ENDPOINT and authenticate with ADMIN_API_KEY.

You’re all set! Pick the option that matches your needs, satisfy the prerequisites, and you’ll be building powerful, MCP-powered workflows in no time.

PreviousExport & IntegrationNextInstallation & Setup

Last updated