Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
mctx-ai avatar

Example MCP Server

  • 2 repo stars
  • Updated July 22, 2026
  • mctx-ai/example-mcp-server

Example MCP Server is an MCP server that demonstrates a complete mctx-ai framework server implementation you can study or fork over remote SSE.

About

Example MCP Server is mctx-ai’s compact reference MCP deployment: same study-or-fork intent as Example App, but focused on the server boundary—schema, remotes, tools, and hosted SSE—without carrying a full application UI. developers in Claude Code or Cursor use it when the next task is register a remote, verify tool lists, and promote a custom server to production-like hosting. The published server.json and versioned URL reduce guesswork for indies who have read the MCP spec but lack a golden sample repo. Fork it, rename tools, and grow into Example App when your product needs pages, auth, and business logic. It is developer scaffolding, not a domain-specific integration; skip it if you only consume third-party MCPs and never author your own.

  • Example MCP Server v1.3.2 hosted at example-mcp-server.mctx.ai via SSE
  • Framework-aligned reference covering @mcp patterns from mctx-ai docs
  • GitHub repo example-mcp-server for fork-and-rename workflows
  • Lighter counterpart to Example App when you only need server wiring

Example MCP Server by the numbers

  • Data as of Jul 23, 2026 (Skillselion catalog sync)
terminal
claude mcp add --transport sse example-mcp-server https://example-mcp-server.mctx.ai/v1.3.2

Add your badge

Show developers this MCP server is listed on Skillselion. Paste this into your README.

Listed on Skillselion
repo stars2
TransportSSE
AuthNone
Last updatedJuly 22, 2026
Repositorymctx-ai/example-mcp-server

What it does

Use the minimal mctx-ai example MCP server as a copy-paste baseline for protocol schema, remote SSE hosting, and tool registration.

Who is it for?

Best when you're authoring your first hosted MCP and want the smallest working reference before scaling to a full app repo.

Skip if: Skip if you already maintain internal MCP templates or only need consumer-side MCP client configuration.

What you get

You connect the hosted example or clone the repo, then reuse its structure to ship your own named MCP server with less protocol trial-and-error.

  • Working example server.json and remote SSE deployment pattern
  • Forkable repo for custom MCP tool handlers
  • Validated tool listing against your client

By the numbers

  • Server version 1.3.2
  • Repository: github.com/mctx-ai/example-mcp-server
  • Schema: modelcontextprotocol.io server.schema.json (2025-12-11 family)
README.md
mctx

Example MCP Server

mctx — The best way to Build an MCP Server

The comprehensive reference implementation for @mctx-ai/mcp. Every framework capability in one well-commented file — clone it, study it, fork it as a template for your own MCP server.


What This Example Demonstrates

src/index.ts covers every pattern the framework supports:

Tool Patterns

  • Sync string returngreet: receives args, returns a formatted string; demonstrates environment variable configuration via GREETING
  • Object returncalculate: returns a structured result object (auto-serialized to JSON); demonstrates input validation and error throwing
  • Progress notificationsanalyze: emits progress via res.progress(current, total); demonstrates streaming updates during long-running operations
  • LLM samplingsmart-answer: delegates to the client's LLM via res.ask; demonstrates graceful fallback when sampling is unavailable
  • User identity via contextwhoami: reads mctx.userId, the stable mctx user ID injected server-side by the platform; demonstrates graceful degradation outside mctx

Resource Patterns

  • Static URIdocs://readme: exact URI, no parameters, returns plain text
  • Dynamic URI templateuser://{userId}: extracts userId from the URI path, returns a JSON profile

Prompt Patterns

  • Single-messagecode-review: returns a plain string that becomes one user message
  • Multi-message conversationdebug: uses conversation() to build structured user/assistant dialogue

Infrastructure

  • Tool annotation hints — every tool sets readOnlyHint, destructiveHint, openWorldHint, and idempotentHint with inline rationale explaining each choice
  • Structured logginglog.info, log.debug, log.warning, log.error, and log.notice throughout
  • Environment variable configuration — reads process.env.GREETING lazily inside the handler (not at module scope)
  • Comprehensive test coveragesrc/index.test.ts tests every tool, resource, and prompt via JSON-RPC 2.0 requests

Usage in Conversation

Once connected to an MCP client, try phrases like these:

Greetings and identity

  • "Greet Alice" — calls greet with name: "Alice"
  • "Who am I?" — calls whoami to return your stable mctx user ID
  • "Greet the whole team" — calls greet in a loop for each name

Math and analysis

  • "What is 6 times 7?" — calls calculate with operation: "multiply"
  • "Divide 10 by 0" — triggers the division-by-zero error path
  • "Analyze quantum computing" — calls analyze and streams three progress phases

Q&A and LLM sampling

  • "What is the capital of France?" — calls smart-answer, which delegates to the client's LLM via ask
  • "Ask anything" — routes arbitrary questions through smart-answer

Resources

  • "Read the server docs" — reads docs://readme
  • "Look up user 42" — reads user://42

Prompts

  • "Review my code" — invokes the code-review prompt with a code snippet
  • "Help me debug this stack trace" — invokes the debug prompt with an error and optional context

Example Responses

greet(name: "Alice")
→ "Hello, Alice!"

whoami()
→ "Your mctx user ID is: user_abc123. This ID is stable across all your devices and sessions."

calculate(operation: "multiply", a: 6, b: 7)
→ { "operation": "multiply", "a": 6, "b": 7, "result": 42 }

analyze(topic: "quantum computing")
→ [progress: 1/3] → [progress: 2/3] → [progress: 3/3]
→ "Analysis of "quantum computing" complete. Found 42 insights across 7 categories."

smart-answer(question: "What is the capital of France?")
→ "Question: What is the capital of France?\n\nAnswer: Paris."

Read URI: docs://readme
→ "Welcome to the example MCP server built with @mctx-ai/mcp..."

Read URI: user://42
→ { "id": "42", "name": "User 42", "joined": "2024-01-01", "role": "developer" }

code-review(code: "const x = eval(input)", language: "javascript")
→ "Please review this javascript for bugs, security issues, and improvements:..."

debug(error: "TypeError: Cannot read properties of undefined")
→ [user] "I'm seeing this error: TypeError: Cannot read..."
→ [assistant] "I will analyze the error and provide step-by-step debugging guidance."

Getting Started

Using as a Template

This repo is a GitHub template. Click Use this template on GitHub, then:

1. Clone your new repo

git clone https://github.com/your-username/your-repo.git
cd your-repo

2. Run the setup script

./setup.sh

setup.sh prompts for a project name and description, asks whether to keep the example code or start from a minimal skeleton, updates package.json, rewrites README.md with a clean starting point, installs dependencies, creates an initial git commit, and deletes itself.

3. Start developing

npm run dev

If you kept the examples, src/index.ts is unchanged — study the patterns and modify from there. If you started empty, you get a minimal skeleton with a single hello tool to build from.

Development Commands

Build

npm run build

Bundles src/index.ts to dist/index.js using esbuild (minified ESM output).

Dev server

npm run dev
# Test environment variables during dev:
GREETING="Howdy" npm run dev

Runs parallel watch mode: esbuild rebuilds on source changes, mctx-dev hot-reloads the server on rebuild.

Testing

npm test                          # Run all tests
npm test -- --watch               # Watch mode
npm test src/index.test.ts        # Specific file
npm test -- -t "greet"            # Pattern match

Linting and formatting

npm run lint
npm run format
npm run format:check

Environment Variables

GREETING — Customizes the greeting in the greet tool (default: "Hello"). Set GREETING="Howdy" to get "Howdy, Alice!".


Project Structure

src/index.ts        → Server implementation — all capabilities in one file
  ├─ Tools          → greet, whoami, calculate, analyze, smart-answer
  ├─ Resources      → docs://readme (static), user://{userId} (dynamic)
  ├─ Prompts        → code-review (single-message), debug (multi-message)
  └─ Export         → fetch handler for JSON-RPC 2.0 over HTTP

src/index.test.ts   → Tests for every tool, resource, and prompt
dist/index.js       → Bundled output (generated by esbuild, not committed on main)

Deployment Model

mctx does not run build commands. It serves dist/index.js from the release branch — no npm run build at deploy time.

dist/ is gitignored on main. The release pipeline (.github/workflows/release.yml) builds dist/index.js from source and commits it to release automatically. Source-only on main; built output on release.

Deployment trigger: mctx watches for version changes in package.json on the release branch. A version bump triggers a new deployment. A push with no version bump does not trigger deployment.

Conventional commits determine the version bump:

Commit prefix Bump
feat!: or fix!: Major
feat: Minor
Everything else Patch

This repo uses squash merging — PR title becomes the commit subject, so PR titles must follow conventional commit format.

Do not edit the release branch directly. Do not commit dist/index.js on main.


Making Your MCP Server Discoverable

Three package.json fields and README.md determine how developers find your MCP server.

  • description — Appears in the MCP Community Registry (truncates at ~100–150 chars) and on your mctx.ai page. Front-load the most important information.
  • homepage — Clickable link on your public mctx.ai page. Point it at your GitHub repo or docs site.
  • README.md — Becomes the documentation on your mctx.ai page and is indexed by Context7 for AI assistant discovery. Lead with what the MCP server does; the first ~4,000 characters are what AI assistants use to understand and recommend it.

Learn More

  • @mctx-ai/mcp — Framework documentation and API reference
  • docs.mctx.ai — Platform guides for deploying and managing your MCP servers
  • mctx.ai — Host your MCP server for free
  • MCP Specification — The protocol spec this MCP server implements

Recommended MCP Servers

How it compares

Minimal server reference MCP, not the full Example App product shell or a vertical data connector.

FAQ

Who is io.github.mctx-ai/example-mcp-server for?

Developers and agent-tool authors who need a small, framework-correct MCP server to learn from or fork before adding product code.

When should I use io.github.mctx-ai/example-mcp-server?

Use it at the start of Build when you are creating custom MCP tools, publishing a remote SSE endpoint, or validating your client against a known-good server.

How do I add io.github.mctx-ai/example-mcp-server to my agent?

Register the remote URL example-mcp-server.mctx.ai for v1.3.2 in your MCP config, or clone github.com/mctx-ai/example-mcp-server and point your client at your local or deployed instance.

Developer Toolsintegrationsbackend

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.