mcp-server-template
Template repository for building a WebAssembly component MCP server using wasmCloud.
README
mcp-server-template
Template repository for creating a WebAssembly component Model Context Protocol (MCP) Server, with wasmCloud.
Dependencies
- Download
wash
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.
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.
<details> <summary>Don't have a Comsonic cluster set up?</summary>
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
</details>
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
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.