mcpField
🧠
🧠 MCP Server Helm Chart

🧠 MCP Server Helm Chart

Local
github.com/lgiupponeCloud & Infra0Updated 74w ago
Repository

About 🧠 MCP Server Helm Chart

MCP Server Helm Chart deploys a configurable MCP server in Kubernetes for teams that want to publish existing REST APIs as tools. It supports remote SSE access and endpoint configuration through values.yaml.

Key features

  1. 01Kubernetes deployment via Helm
  2. 02Remote access over SSE
  3. 03REST endpoints registered as tools
  4. 04Configuration through values.yaml
  5. 05Compatibility with common REST services

Use cases

  1. 01Deploy an MCP server in a cluster
  2. 02Expose application API endpoints to agents
  3. 03Configure available tools for MCP clients

MCP support

The chart deploys an MCP server that exposes configured REST API endpoints as tools. MCP clients connect remotely over SSE at the server's /sse endpoint.

#mcp#mcp-server#helm-chart

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

🧠 MCP Server Helm Chart

This Helm chart dynamically deploys an MCP (Model Context Protocol) server, accessible remotely via Server-Sent Events (SSE). It allows you to easily expose any existing REST API from your application as tools within the MCP environment, enabling intelligent agents or external clients to query and use them.

🚀 Features

  • Deploy an MCP server in a Kubernetes cluster
  • Enable remote interaction via SSE
  • Dynamically register and expose API endpoints as tools
  • Lightweight configuration via values.yaml
  • Compatible with FastAPI, Express, Flask, and any REST service

📦 Chart Structure

mcp-server/
├── Chart.yaml
├── values.yaml
└── templates/
    ├── deployment.yaml
    ├── service.yaml
    ├── ingressroute.yaml
    └── configmap.yaml

⚙️ Dynamic Configuration

You can define which APIs to expose directly in your values.yaml file using the config.tools section. Here's an example configuration:


config:
  tools: |
    tools:
      get_api_status:
        endpoint: https://api-users.dev.example.com/
        description: Get root message to verify the API is running.

      fetch_user_by_id:
        endpoint: https://api-users.dev.example.com/users/1
        description: Fetch a specific user by ID from the API.

      get_random_user:
        endpoint: https://api-users.dev.example.com/users/random
        description: Retrieve a randomly selected user (for testing/demo).

🔒 Make sure to replace *.dev.example.com with your actual domains.

🧪 Install the Chart

helm install mcp-server ./mcp-server \
  --values values.yaml

🔌 MCP Client Configuration

Once deployed, clients can connect to your MCP server using the following configuration:

{
  "mcp": {
    "servers": {
      "users-api": {
        "url": "https://mcp-server.dev.example.com/sse"
      }
    }
  }
}

🔁 The MCP server uses SSE (/sse) to stream messages in real-time.

🧹 Uninstall

helm uninstall mcp-server

🧠 About MCP

MCP (Model Context Protocol) is a lightweight interaction layer that enables intelligent agents or applications to access domain-specific tools using natural language interfaces or direct API querying.

📬 Questions / Contributions

Feel free to open an issue or submit a pull request. Contributions are welcome!

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.