Skip to main content
Glama
cosmonic-labs

mcp-server-template

by cosmonic-labs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

mcp-server-template

Template repository for creating a WebAssembly component Model Context Protocol (MCP) Server, with wasmCloud.

Dependencies

Quickstart

Start the Development loop

Build the component:

npm install
npm run dev

To debug your component, we recommend using the official MCP model inspector, to run that you can run:

npm run inspector

Using the model inspector you can connect to the local MCP server via HTTP, manipulate resources, run tools, and more.

Related MCP server: MY MCP

Generate a MCP Server from our template

1. Use our golden template to build a repository:

wash new <...>

Set up Cosmonic Control

Once your MCP server is ready for primetime, ensure your Comonic cluster is running.

First, sign up for a FREE Cosmonic license.

Once you have a license key, you can set up a Cosmonic cluster on any Kubernetes cluster that supports Helm:

helm install cosmonic-control oci://ghcr.io/cosmonic/cosmonic-control \
  --version 0.2.0 \
  --namespace cosmonic-system \
  --create-namespace \
  --set cosmonicLicenseKey="<insert license here>"

helm install hostgroup oci://ghcr.io/cosmonic/cosmonic-control-hostgroup --version 0.2.0 --namespace cosmonic-system --set http.enabled=true

Deploy the application

With the operator up and running we can start a HostGroup, which is a set of wasmCloud instances that are configured to work together.

With Helm CLI

# Note substitue your own pushed image
helm install weather-gov-mcp oci://ghcr.io/cosmonic-labs/charts/http-sample \
  -n weather-gov --create-namespace \
  --set component.image=ghcr.io/cosmonic-labs/components/weather-gov-mcp:0.1.0 \
  --set component.name=weather-gov-mcp

Connect to the deployed MCP server

If running with a k8s cluster, you can port forward:

kubectl -n cosmonic-system port-forward svc/hostgroup-default 9091:9091

Once you have a local port forward configured to your Cosmonic Control cluster, use the official MCP model inspector to connect.

You can start the MCP inspector via the following command:

npm run inspector

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Xava Labs MCP Template

    null-shot
    A
    license
    Not graded
    quality
    C
    maintenance
    A template repository for building Model Context Protocol (MCP) servers that enables developers to create interactive AI agents with real-time bidirectional communication capabilities through WebSocket and SSE endpoints.
    MIT

  • MY MCP

    vaheandonians
    F
    license
    B
    quality
    D
    maintenance
    A template MCP server that provides a basic structure and configuration for building Model Context Protocol servers. Includes Docker support, environment configuration, and examples for both STDIO and SSE transport modes.
    1
    -

  • Hello World MCP Server

    Auxin-io
    -
    license
    C
    quality
    Not graded
    maintenance
    A simple boilerplate MCP server that provides a basic greeting tool for demonstration purposes. Serves as a starting template for developers to quickly create and deploy custom MCP servers.
    1
    4 npm
    -

  • Streamable HTTP Python MCP

    ferrants
    F
    license
    Not graded
    quality
    D
    maintenance
    A starter template for building MCP servers in Python using the streamable HTTP transport protocol. Provides a foundation with the MCP Python SDK and example configuration to quickly develop custom MCP servers.
    2
    -