{"type":"mcp_server","name":"quick-mcp-example","description":"This repository standardizes LLM interaction with MCP servers, which expose tools, execute functions, provide static content, and offer preset prompts through a unified framework. This repository standardizes LLM interaction with","category":"AI","language":"Python","stars":62,"forks":6,"owner":"ALucek","github_url":"https://github.com/ALucek/quick-mcp-example","homepage":"https://lucek.ai","setup":"## Setup\n\n1. Clone the Repo\n```\ngit clone https://github.com/ALucek/quick-mcp-example.git\ncd quick-mcp-example\n```\n\n2. Create the ChromaDB Database\n\nFollow the instructions in [MCP_setup.ipynb](./MCP_setup.ipynb) to create the vector database and embed a pdf into it.\n\n3. Create the Virtual Environment and Install Packages\n```\n# Using uv (recommended)\nuv venv\nsource .venv/bin/activate  # On macOS/Linux\n# OR\n.venv\\Scripts\\activate     # On Windows\n\n# Install dependencies\nuv sync\n```\n\n4. Run the Client & Server\n\n```\npython client.py mcp_server.py\n```","tools":"## Available Tools\n\n1. Tools (functions that the LLM can invoke to perform actions or retrieve information).\n2. Resources (data sources that can be accessed by the client application).\n3. Prompts (reusable templates that define specific interaction patterns).\n4. Query a vector database for RAG responses.\n5. Choose existing resources to provide context.\n6. Execute standard prompts for more complex analytical workflows.","faq":null,"created_at":"2025-03-04T00:14:45+00:00","updated_at":"2025-03-28T08:43:02+00:00","source_url":"https://model-context-protocol.com/servers/llm-mcp-tools-resources-prompts-example","related_articles":[]}