Skip to main content
Glama
mcp-server-demo

mcp-server-demo

MCP-Server-Demo (Python)

Ein von Grund auf neu erstellter lokaler MCP-Server mit zwei Tools:

  • weather(city) → aktuelles Wetter über wttr.in

  • query_db(sql) → schreibgeschützte SQLite-SELECT-Abfrage

1) Einrichtung

python -m venv .venv
source .venv/bin/activate
pip install -U pip
pip install -e .

Related MCP server: Swiss Meteo MCP

2) MCP-Server ausführen

mcp-server-demo

Dies startet den lokalen Server und erstellt automatisch demo.db mit Beispielzeilen.

3) Schnelle manuelle MCP-Prüfung (optional)

Wenn Sie den MCP Inspector installiert haben:

npx @modelcontextprotocol/inspector

Verbinden Sie sich dann mit Ihrem lokalen Python-Server.

4) Option zur OpenAI-API-Integration

  1. Kopieren Sie die env-Datei und tragen Sie den Schlüssel ein:

cp .env.example .env
  1. Starten Sie den Server in einem Terminal.

  2. Führen Sie in einem zweiten Terminal Folgendes aus:

python client_openai_api.py

Hinweis: Dies verwendet die OpenAI Responses API mit einer MCP-Tool-Definition, die auf http://localhost:8000/mcp verweist.

Tool-Verhalten

weather(city: str)

Gibt JSON-Zusammenfassungsfelder zurück, einschließlich Temperatur, gefühlter Temperatur, Luftfeuchtigkeit, Wind und kurzen Wetterbedingungen.

query_db(sql: str)

  • Erlaubt nur SELECT ...-Abfragen.

  • Gibt Zeilen als JSON zurück.

  • Lehnt Nicht-SELECT-SQL aus Sicherheitsgründen in dieser Starter-Demo ab.

Projektdateien

  • server.py — FastMCP-Server + Tool-Definitionen.

  • client_openai_api.py — einfacher OpenAI-API-Aufruf, der MCP-Tools aufrufen kann.

  • pyproject.toml — Abhängigkeiten + Skript-Einstiegspunkt.

Available Tools

10 tools
analyze_image_with_openaiC

Analyze an image file with an OpenAI vision-capable model.

Inputs: path (required), prompt (required), model. Returns: result

inspect_fileC

Return file metadata and content preview for text/csv/image workflows.

Inputs: path (required), preview_chars, include_base64. Returns: result

list_directoriesC

List directories directly inside a folder within MCP_FILE_OPS_ROOT.

Inputs: path. Returns: result

list_filesB

List files directly inside a folder within MCP_FILE_OPS_ROOT.

Inputs: path. Returns: result

make_directoryC

Create a directory inside MCP_FILE_OPS_ROOT.

Inputs: path (required). Returns: result

move_fileC

Move a file from source_path to destination_path inside MCP_FILE_OPS_ROOT.

Inputs: source_path (required), destination_path (required). Returns: result

move_files_by_globC

Move all files matching a glob pattern from source_dir into destination_dir.

Inputs: source_dir (required), pattern (required), destination_dir (required). Returns: result

query_dbA

Run a read-only SELECT query against local SQLite demo.db.

Inputs: sql (required). Returns: result

read_fileC

Read a UTF-8 text file inside MCP_FILE_OPS_ROOT.

Inputs: path (required). Returns: result

weatherB

Return current weather for a city using wttr.in.

Inputs: city (required). Returns: result

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    C2.9/5.0

    Scored across 10 tools

    Disambiguation4/5

    Most tools have distinct purposes, but there is some overlap between inspect_file and read_file (both provide file content), and move_file vs move_files_by_glob are similar in name and action.

    Naming Consistency4/5

    Majority follow verb_noun pattern with underscores, but 'weather' is a lone noun and 'analyze_image_with_openai' is verbose and breaks the pattern.

    Tool Count4/5

    10 tools is a reasonable number, but the server covers multiple unrelated domains (files, DB, weather, image), making it feel a bit scattered.

    Completeness2/5

    File operations lack delete/copy, DB only has read-only query, weather and image analysis are single-tool services. The surface is incomplete for any single domain.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      C
      quality
      D
      maintenance
      An experimental MCP server that provides weather information tools, including temperature lookup via wttr.io, along with note-taking capabilities for learning MCP server development with GitHub Copilot.
      3
      -
    • F
      license
      Not graded
      quality
      D
      maintenance
      A demo MCP server that provides AI assistants access to live US weather data via the free National Weather Service API, offering forecast and alert tools without requiring an API key.
      -
    • F
      license
      Not graded
      quality
      D
      maintenance
      A lightweight MCP server providing tools for adding integers, getting current time, and fetching weather forecasts via wttr.in.
      -