Skip to main content
Glama
mcp-starter-kit
by junna-legal

Production-Ready MCP Server Boilerplate

Ship reliable MCP servers in minutes, not days. A production-ready foundation for building Model Context Protocol servers with built-in security, authentication, and observability.

NOTE

This is a starter template β€” not a finished product. You are responsible for reviewing and securing any code before production use.

TypeScript License: MIT MCP Compliant

Don't build from scratch. This kit solves the "boring" parts of MCP server developmentβ€”transport management, error handling, and security boundariesβ€”so you can focus on your tool's logic.

Works with Claude Code, Cursor, Windsurf, and any MCP-compatible client.


πŸš€ Why this boilerplate?

Most MCP tutorials show you a "toy" server. This repo gives you a production-grade foundation.

πŸ›‘οΈ Secure by Design

  • SSRF Protection: Blocks requests to private/internal networks (IPv4 + IPv6), including cloud metadata endpoints (169.254.169.254). DNS resolution is checked to prevent rebinding.

  • JWT Security: Algorithm validation rejects alg:none, HS384, and RS256 downgrade attacks. Expiry and tampering are verified with constant-time comparison.

  • HMAC-SHA256 Webhook Signatures: Outbound webhooks are signed with X-Webhook-Signature when a secret is configured.

  • DNS Rebinding Protection: HTTP transport validates Host header against an allowlist.

  • Sandboxed File Access: Prevents AI from reading/writing outside allowed directories, with symlink escape detection.

  • Strict Input Validation: All tool inputs are validated with Zod schemas.

  • Injection Protection: SQLite queries use strict parameter binding.

  • Security tested: 30+ security-focused test cases covering OWASP top threats (SSRF, injection, path traversal, auth bypass).

πŸ”Œ Built for Real Projects

  • Authentication: Built-in strategies for API Key and JWT (configurable per env).

  • Rate Limiting: Token bucket algorithm to prevent abuse.

  • Observability: Structured JSON logging (via pino) ready for CloudWatch/Datadog.

⚑ Developer Experience (DX)

  • Type-Safe: strict: true TypeScript configuration, ESM, fully typed.

  • Testing: 228 tests (unit, integration, and E2E) with Vitest, including 30+ security-focused cases.

  • Dockerized: Multi-stage Dockerfile for immediate deployment.


Related MCP server: mcp-server-toolkit

πŸ“¦ What's Included

Feature

This Boilerplate

Basic Tutorials

Transport

HTTP (SSE) + Stdio

Stdio only

Validation

Zod Schemas

Manual / None

Logging

Structured JSON

console.log

Error Handling

Graceful + MCP Codes

Process crash

CI/CD

GitHub Actions

None

Reference Implementations

Includes 6 fully-typed tools to copy-paste patterns from:

  1. database-query: Secure SQLite operations.

  2. api-connector: Fetch data from external REST APIs.

  3. file-manager: Safe file system operations (5 sub-tools).

  4. cache-store: TTL-based key-value cache with namespaces (5 sub-tools).

  5. semantic-search: Local RAG with embeddings (3 tools + 2 resources + 1 prompt).

  6. webhook-notifier: Async webhook delivery with task tracking (4 tools + 2 resources + 1 prompt).


🏁 Quick Start

Prerequisites

  • Node.js 22+

    WSL2 users: Use Node.js installed inside WSL, not Windows. See Troubleshooting.

  • npm 9+

1. Setup

git clone <your-repo-url> my-mcp-server
cd my-mcp-server
npm install

2. Configure Environment

cp .env.example .env
# Edit .env if needed β€” defaults work out of the box

3. Seed Sample Database

npm run db:seed  # Populates local SQLite for testing

Note: If the server is already running, restart it after seeding to pick up the new database.

4. Build

npm run build  # Compiles TypeScript to dist/

5. Run Development Server

npm run dev
# Starts server in hot-reload mode

6. Verify with Inspector

npm run inspector
# Opens interactive debugger in your browser (uses dist/index.js)

πŸ”§ Connecting to Clients

Claude Code

Copy the example config to your project root:

cp .mcp.json.example .mcp.json
# Edit paths in .mcp.json to match your setup

Or add manually to your .mcp.json:

{
  "mcpServers": {
    "mcp-starter-kit": {
      "command": "node",
      "args": ["dist/index.js"],
      "env": {
        "LOG_LEVEL": "info",
        "DB_PATH": "./data/sample.db",
        "SANDBOX_ROOT": "./data/sandbox"
      }
    }
  }
}

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "my-production-server": {
      "command": "node",
      "args": ["/absolute/path/to/my-mcp-server/dist/index.js"]
    }
  }
}

Cursor, Windsurf, & Others

See docs/SETUP.md for detailed connection guides.


πŸ“‚ Project Architecture

Designed for scalability:

mcp-starter-kit/
β”œβ”€β”€ src/
β”‚   β”œβ”€β”€ index.ts              # Entry point
β”‚   β”œβ”€β”€ server.ts             # Central MCP registry
β”‚   β”œβ”€β”€ config/env.ts         # Environment variable validation (Zod)
β”‚   β”œβ”€β”€ tools/
β”‚   β”‚   β”œβ”€β”€ database-query/   # SQLite CRUD tool
β”‚   β”‚   β”œβ”€β”€ api-connector/    # REST API tool
β”‚   β”‚   β”œβ”€β”€ file-manager/     # Sandboxed file operations tool
β”‚   β”‚   β”œβ”€β”€ cache-store/      # TTL-based key-value cache
β”‚   β”‚   β”œβ”€β”€ semantic-search/  # Local RAG with embeddings
β”‚   β”‚   └── webhook-notifier/ # Async webhook delivery
β”‚   β”œβ”€β”€ lib/                  # Shared utilities (Logger, Guardrails)
β”‚   β”œβ”€β”€ middleware/            # Auth & rate limiting
β”‚   └── transport/            # stdio and HTTP transports
β”œβ”€β”€ tests/                    # Integration tests & helpers
β”œβ”€β”€ scripts/                  # CLI tools (db:seed, create-tool)
β”œβ”€β”€ docs/                     # Detailed documentation
β”œβ”€β”€ docker/                   # Dockerfile & docker-compose
└── data/                     # Sample DB & sandbox directory

πŸ“œ Documentation

Document

Description

SETUP.md

Detailed setup, environment variables, client configuration

CUSTOMIZATION.md

Step-by-step guide to creating new tools

DEPLOYMENT.md

Deploy via npm, Docker, or cloud services

ARCHITECTURE.md

Design decisions, security model, and data flow

TROUBLESHOOTING.md

Common errors and solutions

TESTING.md

Test suite organization, writing tests, security checklist

SECURITY.md

Security policy, vulnerability reporting, feature inventory


πŸ› οΈ Scripts

Command

Description

npm run dev

Start with hot-reload (tsx watch)

npm run build

Build to dist/ (tsup)

npm start

Run built server (stdio)

npm run start:http

Run built server (HTTP)

npm test

Run all tests

npm run lint

Lint with ESLint

npm run typecheck

Type-check with tsc

npm run inspector

Open MCP Inspector

npm run db:seed

Seed sample SQLite database

npm run create-tool

Scaffold a new tool

npm run test:coverage

Run tests with coverage report


License

MIT Β© 2026 Edge Craft Studio

Not affiliated with, endorsed by, or certified by Anthropic or the Agentic AI Foundation.

Available Tools

15 tools
api-connectorA

Make HTTP requests to any REST API with custom headers, JSON body, retry, and configurable timeout. Returns the response status, headers, and body.

Inputs: url (required), body, method, headers, +3 more.

cacheC

Key-value cache with TTL and namespaces. Operations: set, get, delete, list, clear.

Inputs: operation (required), key, value, namespace, +1 more.

database-queryA

Execute SQL queries against a SQLite database (SELECT, INSERT, UPDATE, DELETE). Use operation 'list-tables' to discover available tables. Mutation queries require 'allow_mutation: true' for safety.

Inputs: operation (required), sql, params, allow_mutation, +1 more.

file_infoA

Get metadata about a file or directory including size, modification date, and permissions.

Inputs: path (required).

file_listA

List entries in a directory. Returns files and subdirectories sorted with directories first.

Inputs: path.

file_readA

Read the contents of a text file. The path must be relative to the sandbox base directory.

Inputs: path (required), encoding.

file_writeA

Write content to a text file. Creates parent directories if needed. Set overwrite to true to replace existing files.

Inputs: path (required), content (required), overwrite.

semantic_clearA

Clear all indexed documents from a collection. This action is irreversible.

Inputs: collection (required).

semantic_indexA

Index a document into a collection for semantic search. Text is automatically chunked and embedded using a local ML model (no API calls). Use document_id to replace an existing document.

Inputs: document (required), collection (required), metadata, document_id.

task_createB

Create an async task for tracking long-running operations. Tasks have a TTL and can optionally trigger webhook notifications on status changes.

Inputs: name (required), metadata, description, ttl_seconds, +1 more.

task_statusA

Get the current status of an async task, or update its status. Supports status transitions: pending->running, running->completed/failed. When a task reaches a terminal state, its configured webhook event is fired.

Inputs: task_id (required), result, update_status.

webhook_registerA

Register a webhook callback URL to receive event notifications. Specify the URL, event types to subscribe to, and an optional HMAC secret for signature verification.

Inputs: url (required), event_types (required), active, secret, +1 more.

webhook_sendA

Send a notification to all registered webhooks matching the event type. Supports idempotency keys to prevent duplicate deliveries and HMAC-SHA256 signatures.

Inputs: event_type (required), payload, idempotency_key.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 15 tools

    Disambiguation5/5

    Each tool targets a distinct resource and action, with clear boundaries between file, database, cache, semantic, webhook, and task operations. The only minor overlap is task_status handling both get and update, but the description clearly separates these behaviors, so no two tools appear to do the same thing.

    Naming Consistency2/5

    Naming conventions are mixed: some tools use hyphens (database-query, api-connector), others use underscores (file_read, task_status), and one is a single word (cache). The word order is also inconsistent, with most tools using noun_verb (file_read) but api-connector using a noun-noun pattern, and no uniform separator across the set.

    Tool Count4/5

    With 15 tools, the server sits at the upper boundary of a reasonable scope for a starter kit. Each tool covers a distinct capability, but the sheer variety (files, database, cache, semantic search, webhooks, tasks) makes it feel slightly broad, yet still justifiable for its purpose.

    Completeness3/5

    The tool surface covers core operations for each domain, but there are notable gaps: no file_delete or file_rename, no webhook_unregister, and no task_cancel or task_delete. These are common lifecycle operations that agents would likely need, making the set somewhat incomplete.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      A production-grade MCP server and client implementation with comprehensive features including structured logging, health checks, metrics, authentication, and RAG capabilities with PostgreSQL vector search. Supports both stdio and SSE transports with containerization and security features for enterprise deployment.
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Production-ready MCP server starter with authentication, observability, and a plugin system for building and deploying MCP servers quickly.
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      A production-ready MCP server template that connects LLMs and AI agents to external data, tools, and services with built-in OAuth 2.1 authentication, Redis-backed session management, and a modular tools engine.
      1
      MIT