Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Quote Collection MCP-Server Find all quotes by Oscar Wilde"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
In this project, you will develop an MCP server for a personal quote collection. The server should make it possible to collect, categorize, and retrieve inspiring quotes in a targeted or random manner.
Framework conditions:
AI-First: Use the AI-First approach and actively use AI tools to support all phases of development.
Persistence: The data must be stored in a JSON file.
Language choice: The implementation language is freely selectable.
Technical robustness: The search must work case-insensitively and the server must handle errors robustly.
Steps:
Planning and conception: Start by selecting a suitable implementation language and decide on the architecture of the MCP server.
Data structure: Define the JSON data structure for persisting the quotes.
Data model and basic functions: Create the data model and implement the basic functions for storage management.
Data model: A quote must contain the following fields:
Unique ID
Text of the quote
Creation date
Tags: Author tag (who said it), topic tag (e.g., "Motivation", "Love"), and language tag (e.g., "German", "English").
Storage: Implement the function to save individual quotes.
Batch import: Enable importing multiple quotes at once.
Example of the data format: { "text": "Be yourself; everyone else is already taken.", "autor_tag": "Oscar Wilde", "themen_tag": "Authentizität", "sprachen_tag": "englisch" }
Search functions and logic: Develop the logic for retrieving and managing the quotes.
Search: Implement a search function that finds quotes based on all three tag types or the text itself (case-insensitive).
Random quote: Create a function that returns a random quote. It should optionally be filterable by specific tags.
Delete: Implement the ability to remove quotes.
MCP server integration: Integrate your logic into the MCP framework to make the server usable.
Integration: Connect the implemented functions (tools) with the MCP interface.
Test: Test the functionality and robustness of the server with Claude or a corresponding MCP client.
Related MCP server: Quote MCP Server
Push your solution to this repository and wait for feedback in the feedback PR.
Add a single new quote to the collection.
Inputs: text (required), topic_tag (required), author_tag (required), language_tag (required).
Delete a quote by its unique ID.
Inputs: id (required).
Import multiple quotes at once.
Inputs: quotes (required).
List every quote currently stored in the collection.
Inputs: no named parameters.
Get a random quote, optionally filtered by author, topic, and/or language tag.
Inputs: topic_tag, author_tag, language_tag.
Search quotes by text or by author/topic/language tag. Case-insensitive substring match.
Inputs: query (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 6 tools
Each tool has a clearly distinct purpose: adding, importing, searching, random selection, deletion, and listing. No two tools overlap in functionality; search and random both filter but serve different intents (finding specific vs. retrieving a random quote).
All tool names follow a consistent verb_noun pattern using snake_caseadd_quote, import_quotes, search_quotes, random_quote, delete_quote, list_quotes). The pattern is uniform and predictable.
Six tools is well within the ideal 3-15 range for a focused domain like a quote collection. Each tool serves a necessary function without redundancy or bloat.
The set covers create (add, import), read (list, search, random), and delete, but lacks an update operation for editing existing quotes. This is a minor gap since quotes are typically static, but an update tool would complete the CRUD lifecycle.
Search, read, cite, create, and safely update a user's private KeepFlash knowledge library.
Search, read, and write highlights, notes, screenshots, collections, projects, and tags in Gleanit.
Search, save, and set reminders in your personal MarkIt library of links, posts, and notes.
