Skip to main content
Glama
deenesjakoruzh
instructa

MCP Starter

by instructa
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript

MCP Server Starter

MCP-Starter

Möchten Sie Ihren eigenen MCP-Server erstellen?

MCP Server Starter bietet Ihnen eine grundlegende Struktur zum Ausführen lokaler Tools mit Cursor, Claude und anderen unter Verwendung des MCP-Standards.

Merkmale

  • 📡 Flexible Kommunikation

    • Unterstützt mehrere Kommunikationsprotokolle zwischen Client und Server,

    • stdio : Lokale Verwendung

    • Streamable HTTP : Remote- und lokale Nutzung

    • sse : Remote- und lokale Nutzung (veraltet)~~

  • 📦 Minimale Einrichtung – Legen Sie schnell mit einer grundlegenden Serverimplementierung los.

  • 🤖 Cursor-KI-Integration – Enthält eine Beispielkonfiguration .cursor/mcp.json .

  • ⌨️ TypeScript – Fügen Sie Ihrem Projekt Typsicherheit hinzu.

Related MCP server: MCP Server Starter

Aufgaben

  • [ ] Option zum Veröffentlichen eigener Pakete hinzufügen

  • [ ] Bessere CLI-Unterstützung für Scaffolding

  • [ ] Aufforderungen zum spontanen Erstellen von Werkzeugen

Erste Schritte

Voraussetzungen

  • Node.js (ggf. Version angeben)

  • Ein MCP-kompatibler Client (z. B. Cursor )

Verwendung

Unterstützte Transportoptionen

Das Model Context Protocol unterstützt mehrere Transportmethoden.

stdio

MCP-Starter

Empfohlen für lokale Setups

Code-Editor-Unterstützung

Fügen Sie die folgenden Codeausschnitte hinzu

  • Cursor: .cursor/mcp.json

Lokale Entwicklung/Tests

Verwenden Sie dies, wenn Sie Ihren MCP-Server lokal testen möchten

{
  "mcpServers": {
    "my-starter-mcp-stdio": {
      "command": "node",
      "args": ["./bin/cli.mjs", "--stdio"]
    }
  }
}

Veröffentlichtes Paket

Verwenden Sie dies, wenn Sie Ihr Paket im npm-Register veröffentlicht haben

{
  "mcpServers": {
    "my-starter-mcp-stdio": {
      "command": "npx",
      "args": ["my-mcp-server", "--stdio"]
    }
  }
}

Streambares HTTP

MCP-Starter

Wichtig: Streamable HTTP wird in Cursor noch nicht unterstützt

Empfohlen für die Remote-Server-Nutzung

Wichtig: Im Gegensatz zu stdio müssen Sie den Server auch mit dem richtigen Flag ausführen

Lokale Entwicklung Verwenden Sie den streamable http Transport

  1. Starten Sie den MCP-Server. Führen Sie dies in Ihrem Terminal aus.

node ./bin/cli.mjs --http --port 4200

Oder mit MCP Inspector

npm run dev-http
# npm run dev-sse (deprecated)

  1. Fügen Sie dies Ihrer Konfiguration hinzu

{
  "mcpServers": {
    "my-starter-mcp-http": {
      "command": "node",
      "args": ["./bin/cli.mjs", "--http", "--port", "4001"]
      // "args": ["./bin/cli.mjs", "--sse", "--port", "4002"] (or deprecated sse usage)
    }
  }
}

Veröffentlichtes Paket

Verwenden Sie dies, wenn Sie Ihr Paket im npm-Register veröffentlicht haben

Führen Sie dies in Ihrem Terminal aus

npx my-mcp-server --http --port 4200
# npx my-mcp-server --sse --port 4201 (deprecated)
{
  "mcpServers": {
    "my-starter-mcp-http": {
      "url": "http://localhost:4200/mcp"
      // "url": "http://localhost:4201/sse"
    }
  }
}

Verwenden des Inspektors

Verwenden Sie den Befehl inspect , um Ihren MCP-Server zu debuggen

MCP-StarterMCP-Starter

Befehlszeilenoptionen

Protokollauswahl

Protokoll

Beschreibung

Flaggen

Hinweise

stdio

Standard-E/A

(Keiner)

Standard

http

HTTP REST

--port <num> (Def.: 3000), --endpoint <path> (Def.: /mcp )

sse

Server-Sent-Ereignisse

--port <num> (def: 3000)

Veraltet

Lizenz

Dieses Projekt ist unter der MIT-Lizenz lizenziert – Einzelheiten finden Sie in der Datei LICENSE.

Kurse

Available Tools

1 tool
doSomethingD

What is the capital of Austria?

ParametersJSON Schema
NameRequiredDescriptionDefault
param1YesThe name of the track to search for
param2YesThe name of the track to search for

TDQS

D1.4/5.0
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description fails to indicate what the tool does, whether it's a read/write operation, any side effects, or response format. It offers no behavioral context beyond the confusing question, leaving the agent with no understanding of the tool's behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, but it is not appropriately sized for the tool—it is under-specified and misleading rather than concise. It does not front-load useful information about the tool's purpose, wasting the opportunity to clarify functionality.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (2 required parameters, no annotations, no output schema) and the description's complete failure to explain the tool's purpose or behavior, it is inadequate. The description does not compensate for the lack of annotations or output schema, leaving the agent with insufficient information to use the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with both parameters documented as 'The name of the track to search for'. The description adds no parameter information beyond what the schema provides. According to the rules, with high schema coverage (>80%), the baseline is 3 even with no param info in the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'What is the capital of Austria?' is a question about geography, not a description of what the tool does. It provides no verb indicating an action (e.g., search, retrieve, calculate) and no mention of resources or operations. This is misleading as it suggests a trivia answer rather than tool functionality.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool. The description does not mention any context, prerequisites, or alternatives. Given the mismatch between the description and input schema (which references track searching), there is no usable information for an agent to determine appropriate usage scenarios.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

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

  1. 1 tool updatev1.0.0
    • First observeddoSomething
Deploy Server
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

TDQS

D1.8/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of confusion or overlap between tools. The tool 'doSomething' stands alone with a distinct purpose, making disambiguation trivial.

Naming Consistency3/5

There is only one tool, so consistency cannot be assessed across multiple tools. The naming 'doSomething' is clear but does not follow a strong pattern, placing it in the middle range.

Tool Count2/5

A single tool is generally too few for most server purposes, as it limits functionality and scope. This feels thin and inadequate for typical MCP server applications.

Completeness1/5

The server has a single tool that answers a specific trivia question, which is severely incomplete for any meaningful domain. There are obvious gaps, as it lacks any operational coverage or lifecycle management.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • MCP Server Python Template

    Cris-0k
    A
    license
    Not graded
    quality
    Not graded
    maintenance
    A streamlined foundation for building Model Context Protocol servers in Python, designed to make AI-assisted development of MCP tools easier and more efficient.
    12
    MIT

  • MCP Server Scaffold

    vjouenne76
    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
    -

  • MCP Template

    xcollantes
    A
    license
    B
    quality
    D
    maintenance
    A template repository for building Model Context Protocol (MCP) servers that enable LLM clients to interact with custom tools and services through standardized JSON-RPC communication.
    3
    MIT

Appeared in Searches