Skip to main content
Glama
RUverse

MCP Server Template

by RUverse

MCP Skill-and-Tools Bundle Template

A Node.js implementation of an MCP (Model Context Protocol) server built on the 2026-07-28 specification: stateless, per-request metadata, Streamable HTTP.

Features

  • MCP 2026-07-28 only: stateless core, server/discover, subscriptions/listen, resultType, cacheable list results, request-metadata headers — no handshake-era code paths to maintain

  • Dynamic Tool Loading: automatically discovers and loads tools from /tools

  • Typed tool results: outputSchema + structuredContent, input validation

  • Canonical skill metadata loaded from skill/SKILL.md into discovery

  • Bearer authentication with an explicitly configured production secret

  • Production container running as a non-root user with a health check

  • Sample Tools: calculator and timestamp for demonstration

Related MCP server: MCP Server Project

What changed in 2026-07-28

The 2026-07-28 revision made MCP a stateless request/response protocol. This server implements that revision and nothing older — a client on 2025-11-25 or earlier gets a 400 telling it which version to use. If you are pointing an existing client at this server, these are the changes that matter:

Removed

Replacement

initialize / notifications/initialized

Per-request _meta on every request

Mcp-Session-Id header, DELETE /mcp

No protocol sessions — pass explicit handles as tool arguments

GET /mcp SSE stream, resources/subscribe

subscriptions/listen (one long-lived POST-response stream)

ping, logging/setLevel, notifications/roots/list_changed

Removed; log level is per-request via _meta

Last-Event-ID resumability, SSE event ids

None — re-issue the request with a new id

Server-initiated sampling/createMessage, elicitation/create, roots/list

Multi Round-Trip Requests (resultType: "input_required")

JSON-RPC batching

One JSON-RPC message per POST

Added: server/discover, the required resultType field on every result, ttlMs/cacheScope on list results, required MCP-Protocol-Version / Mcp-Method / Mcp-Name headers, x-mcp-header tool parameters, and the -32020/-32021/-32022 error codes. Roots, Sampling and Logging are now deprecated and are not advertised by this server.

Quick Start

  1. Describe the skill: edit skill/SKILL.md. Its frontmatter becomes the server identity and marketplace description; its Markdown body becomes server/discover.instructions.

  2. Add or edit tools: place one module per tool under tools/.

  3. Install dependencies:

npm install
  1. Set up environment and replace the example Bearer key:

cp .env.example .env
  1. Run the tests:

npm test

Run npm run test:container when Docker is available to verify non-root startup, the image health check, and failure when MCP_API_KEY is missing.

  1. Start the server:

npm start

Server runs on http://127.0.0.1:3202.

🔐 Authentication

Set MCP_API_KEY to a non-placeholder secret before the process starts. The server exits immediately when it is absent or still set to the example value. MCP requests accept credentials only through the standard Bearer header:

curl -X POST -H "Authorization: Bearer your-api-key" http://127.0.0.1:3202/mcp

Query-string credentials and X-API-Key are rejected. A 401 carries a plain WWW-Authenticate: Bearer challenge. OAuth is intentionally not advertised by this template until a complete OAuth 2.1/OIDC implementation is provided.

📡 Talking to the server

Every request carries its protocol version, client identity and capabilities in params._meta, and mirrors method (and name/uri) into HTTP headers. A mismatch between headers and body is rejected with 400 and error -32020.

Discovery

curl -X POST http://127.0.0.1:3202/mcp -H "Authorization: Bearer your-api-key" -H "Content-Type: application/json" -H "Accept: application/json, text/event-stream" -H "MCP-Protocol-Version: 2026-07-28" -H "Mcp-Method: server/discover" -d '{"jsonrpc":"2.0","id":1,"method":"server/discover","params":{"_meta":{"io.modelcontextprotocol/protocolVersion":"2026-07-28","io.modelcontextprotocol/clientInfo":{"name":"curl","version":"1.0.0"},"io.modelcontextprotocol/clientCapabilities":{}}}}'

Calling a tool

tools/call additionally requires the Mcp-Name header, matching params.name:

curl -X POST http://127.0.0.1:3202/mcp -H "Authorization: Bearer your-api-key" -H "Content-Type: application/json" -H "Accept: application/json, text/event-stream" -H "MCP-Protocol-Version: 2026-07-28" -H "Mcp-Method: tools/call" -H "Mcp-Name: calculator" -d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"calculator","arguments":{"operation":"multiply","operand1":7,"operand2":8},"_meta":{"io.modelcontextprotocol/protocolVersion":"2026-07-28","io.modelcontextprotocol/clientCapabilities":{}}}}'

Response:

{
  "jsonrpc": "2.0",
  "id": 2,
  "result": {
    "resultType": "complete",
    "content": [{ "type": "text", "text": "{\"operation\":\"multiply\",\"operands\":[7,8],\"result\":56}" }],
    "structuredContent": { "operation": "multiply", "operands": [7, 8], "result": 56 },
    "_meta": { "io.modelcontextprotocol/serverInfo": { "name": "mcp-utility-tools", "version": "2.0.0" } }
  }
}

Add "progressToken" to _meta and send Accept: text/event-stream to get the response as a stream with notifications/progress ahead of the result.

Change notifications

curl -N -X POST http://127.0.0.1:3202/mcp -H "Authorization: Bearer your-api-key" -H "Content-Type: application/json" -H "Accept: text/event-stream" -H "MCP-Protocol-Version: 2026-07-28" -H "Mcp-Method: subscriptions/listen" -d '{"jsonrpc":"2.0","id":1,"method":"subscriptions/listen","params":{"notifications":{"toolsListChanged":true},"_meta":{"io.modelcontextprotocol/protocolVersion":"2026-07-28","io.modelcontextprotocol/clientCapabilities":{}}}}'

The first message is notifications/subscriptions/acknowledged, echoing the filters the server will honour. Every message on the stream is tagged with io.modelcontextprotocol/subscriptionId. Run with MCP_WATCH_TOOLS=true and edit a file in tools/ to see notifications/tools/list_changed arrive.

Closing the stream is the cancellation signal — there is no DELETE.

🛠️ Available Tools

Tool

Description

calculator

Add, subtract, multiply, divide — returns structuredContent

timestamp

Current time as ISO 8601, Unix epoch, or human-readable

⚙️ Creating Your Bundle

The repeatable workflow is: edit skill/SKILL.md, add modular tools, run npm test, deploy the server over public HTTPS, then use Connect & import in RUverse. The default bundle already satisfies RUverse's name, 20–240 character description, and 2,000-character instruction limits.

1. Tool File Structure

Create tools/your-tool.js:

const TOOL_DEFINITION = {
    name: "your_tool",
    title: "Your Tool",
    description: "What your tool does",
    inputSchema: {
        type: "object",
        properties: {
            param1: { type: "string", description: "Parameter description" }
        },
        required: ["param1"],
        additionalProperties: false
    },
    // Optional but recommended: lets clients validate structuredContent.
    outputSchema: {
        type: "object",
        properties: { result: { type: "string" } },
        required: ["result"]
    }
};

async function execute(args = {}, context = {}) {
    const { param1 } = args;

    // context.reportProgress({ progress, total, message }) streams progress
    // when the client sent a progressToken.
    // context.signal aborts when the client closes the stream.
    // context.clientInfo / context.clientCapabilities describe the caller.

    const structuredContent = { result: `Processed: ${param1}` };

    return {
        content: [{ type: "text", text: JSON.stringify(structuredContent) }],
        structuredContent
    };
}

module.exports = { definition: TOOL_DEFINITION, execute };

Arguments are validated against inputSchema before execute runs. Throwing from execute produces a tool execution error (isError: true) rather than a JSON-RPC error, so the model can self-correct.

2. Auto-Loading

Save the file in /tools and restart the server (or set MCP_WATCH_TOOLS=true to hot-reload and notify subscribers).

3. Stateful tools

MCP has no protocol-level session. If a tool needs state across calls, return an opaque handle and accept it as an argument on later calls — document its lifetime in the tool description so the model knows when to create a new one.

4. Asking the client for input (MRTR)

Instead of sending a server-initiated elicitation/create request, return an input-required result and let the client retry:

return {
    resultType: "input_required",
    inputRequests: {
        github_login: {
            method: "elicitation/create",
            params: {
                mode: "form",
                message: "Please provide your GitHub username",
                requestedSchema: {
                    type: "object",
                    properties: { name: { type: "string" } },
                    required: ["name"]
                }
            }
        }
    },
    // Anything you need to resume; it comes back on the retry.
    requestState: "..."
};

The retry arrives as a new tools/call with context.inputResponses and context.requestState populated.

5. Exposing a parameter as an HTTP header

Annotate a primitive, statically reachable property with x-mcp-header so intermediaries can route on it without parsing the body:

region: { type: "string", description: "...", "x-mcp-header": "Region" }

Conforming clients then send Mcp-Param-Region: us-west1, and the server rejects any request where the header and the argument disagree. Never annotate secrets — header values are visible to every intermediary on the path.

🔗 MCP Client Integration

{
  "mcpServers": {
    "template": {
      "type": "http",
      "url": "http://127.0.0.1:3202/mcp",
      "headers": {
        "Authorization": "Bearer your-api-key"
      }
    }
  }
}

Production deployment

Build and run the included non-root container behind a public HTTPS reverse proxy. Never bake the Bearer secret into the image or repository:

docker build -t my-mcp-bundle .
docker run --read-only --tmpfs /tmp --cap-drop=ALL \
  -e MCP_API_KEY='replace-with-a-long-random-secret' \
  -p 127.0.0.1:3202:3202 my-mcp-bundle

Terminate TLS at your ingress, proxy a public URL such as https://mcp.example.com/mcp to port 3202, and pass the same key to RUverse as the endpoint's Bearer credential. Keep /health available to the container platform. Configure MCP_ALLOWED_ORIGINS only when browser clients need direct access. The default private cache scope prevents authenticated discovery and tool lists from being shared across authorization contexts.

📁 Layout

mcp-server.js        Express app, routing, request validation, dispatch
skill/SKILL.md       Canonical marketplace metadata and runtime instructions
lib/skill.js         Startup loader and RUverse constraint validation
lib/protocol.js      Version constants, _meta keys, error codes, message builders
lib/headers.js       Request-metadata headers, base64 sentinel, x-mcp-header
lib/schema.js        Tool argument validation
lib/sse.js           SSE response streams (no resumability, per spec)
lib/subscriptions.js subscriptions/listen stream management
lib/security.js      Origin validation and Bearer-only authentication
tools/               Auto-loaded tools
test/                Protocol, bundle, security, and official-client tests
Dockerfile           Non-root production image with /health check

Endpoints

Endpoint

Purpose

POST /mcp

The MCP endpoint — the only method it accepts

GET /mcp, DELETE /mcp

405: the standalone SSE stream and session termination are gone

GET /health

Status, protocol version, open subscriptions

GET /tools/config

Tool definitions for wiring into an agent config

License

MIT — see LICENSE.

This server is provided as-is for demonstration purposes. Please review and enhance security measures before production use.

A
license - permissive license
Not graded
quality - not tested
C
maintenance

Maintenance

UpdatingMaintainers
UpdatingResponse time
Release cycle
0Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • F
    license
    B
    quality
    D
    maintenance
    A basic starter project for building Model Context Protocol (MCP) servers that enables standardized interactions between AI systems and various data sources through secure, controlled tool implementations.
    2
  • A
    license
    Not graded
    quality
    D
    maintenance
    A template/boilerplate MCP server for building custom tools and integrations that enable seamless connections between AI applications and external data sources.
    225
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    A minimal template MCP server demonstrating basic tools, resources, and prompts functionality. Includes example implementations like a hello tool, history resource, and greet prompt for learning MCP development.
    2
    ISC
  • A
    license
    Not graded
    quality
    D
    maintenance
    A bare-bones FastMCP server template designed to serve as a starting point for building custom Model Context Protocol servers. It provides a foundational structure for implementing tools over HTTP and includes a built-in health check utility.
    GPL 3.0

View all related MCP servers

Related MCP Connectors

  • MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.

  • MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.

  • MCP server exposing the Backtest360 engine API as tools for AI agents.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/RUverse/mcp-server-template'

If you have feedback or need assistance with the MCP directory API, please join our Discord server