Discover Awesome MCP Servers

wayne-mcp-servers

My custom MCP (Model Context Protocol) servers.

mcp-server-on-raspi MCP serverWhat is MCP Server on Raspberry Pi?How to use MCP Server on Raspberry Pi?Key features of MCP Server on Raspberry Pi?Use cases of MCP Server on Raspberry Pi?FAQ from MCP Server on Raspberry Pi?

Sistem penyimpanan catatan sederhana yang memungkinkan pengguna membuat dan meringkas catatan dengan berbagai tingkat detail menggunakan Claude.

connector-GitHubTestRepo

created from MCP server demo

Mcp Translate

Okay, I understand. Please provide the English text you would like me to translate into Indonesian using the Model Context Protocol. I will do my best to provide an accurate and contextually appropriate translation.

evm-server MCP Server

Mirror of

MCP Server Template

Kit pemula MCP untuk membangun alat AI dengan runtime Bun - dikhususkan untuk kuis interaktif.

blender-open-mcp

Sebuah server yang mengintegrasikan Blender dengan model AI lokal melalui Protokol Konteks Model, memungkinkan pengguna untuk mengendalikan Blender menggunakan perintah bahasa alami untuk tugas-tugas pemodelan 3D.

usaspending-mcp

I understand you're looking for a way to interact with the USASpending.gov API using an MCP server. However, "MCP server" is a very broad term. To give you the best possible advice, I need more information. "MCP" could refer to several things. Here's a breakdown of what I need to know and some general approaches: **1. What do you mean by "MCP Server"?** * **Minecraft Server Protocol (MCP):** Is this related to Minecraft? It's unlikely, but possible you're trying to use a Minecraft server as an intermediary. If so, please explain the connection. * **Management Control Program (MCP):** This is a very old operating system from Burroughs. It's highly unlikely you're using this. * **Something else entirely?** Please provide more context. What software or system are you referring to when you say "MCP server"? What is its purpose in your intended architecture? **2. What are you trying to achieve with the USASpending.gov API?** * **Data Extraction:** Are you trying to download specific datasets? * **Data Analysis:** Are you trying to perform calculations or visualizations on the data? * **Integration with another system:** Are you trying to feed the data into another application? * **Specific endpoints:** Do you know which USASpending.gov API endpoints you need to use (e.g., `/awards/`, `/transactions/`, `/references/toptier_agencies/`)? **3. What programming languages and tools are you comfortable with?** * **Python:** A popular choice for API interaction and data analysis. Libraries like `requests` and `pandas` are very helpful. * **Java:** Another common language for server-side development. * **JavaScript:** Useful for front-end applications that interact with the API. * **Other languages:** Let me know if you're using something else. **General Approaches (Assuming a Generic Server):** Assuming "MCP server" refers to a generic server environment (e.g., a Linux server running a web server), here's a general outline of how you could interact with the USASpending.gov API: 1. **Choose a Programming Language:** Select a language suitable for server-side development and API interaction (e.g., Python, Java, Node.js). 2. **Install Necessary Libraries:** Install the libraries needed to make HTTP requests and process JSON data. For example: * **Python:** `requests`, `json` * **Java:** `java.net.http`, `org.json` * **Node.js:** `node-fetch`, `axios` 3. **Write Code to Interact with the API:** Write code to: * Construct the API request URL (including any necessary parameters). * Make the HTTP request to the USASpending.gov API. * Handle the API response (check for errors, parse the JSON data). * Store or process the data as needed. 4. **Deploy the Code to your "MCP Server":** Deploy your code to the server environment. This might involve: * Copying the code files to the server. * Installing the necessary runtime environment (e.g., Python interpreter, Java runtime). * Configuring the server to run your code (e.g., using a web server like Apache or Nginx). 5. **Schedule or Trigger the Code:** Determine how you want to run the code: * **Scheduled task:** Use a cron job or similar scheduler to run the code periodically. * **API endpoint:** Create an API endpoint on your server that triggers the code when called. **Example (Python):** ```python import requests import json def get_usaspending_data(endpoint, params=None): """ Fetches data from the USASpending.gov API. Args: endpoint: The API endpoint to call (e.g., '/awards/'). params: A dictionary of query parameters. Returns: A JSON object containing the API response, or None if an error occurred. """ base_url = "https://api.usaspending.gov/api/v2" # Replace with the correct API version if needed url = f"{base_url}{endpoint}" try: response = requests.get(url, params=params) response.raise_for_status() # Raise an exception for bad status codes return response.json() except requests.exceptions.RequestException as e: print(f"Error fetching data: {e}") return None # Example usage: Get the latest 10 awards awards = get_usaspending_data("/awards/", params={"limit": 10}) if awards: print(json.dumps(awards, indent=2)) # Pretty print the JSON # Process the awards data here else: print("Failed to retrieve awards data.") ``` **Translation of the above explanation to Indonesian:** Saya mengerti Anda ingin berinteraksi dengan USASpending.gov API menggunakan server MCP. Namun, "server MCP" adalah istilah yang sangat luas. Untuk memberikan saran terbaik, saya membutuhkan informasi lebih lanjut. "MCP" bisa merujuk pada beberapa hal. Berikut adalah rincian informasi yang saya butuhkan dan beberapa pendekatan umum: **1. Apa yang Anda maksud dengan "Server MCP"?** * **Minecraft Server Protocol (MCP):** Apakah ini terkait dengan Minecraft? Kemungkinan kecil, tetapi mungkin Anda mencoba menggunakan server Minecraft sebagai perantara. Jika ya, jelaskan hubungannya. * **Management Control Program (MCP):** Ini adalah sistem operasi yang sangat lama dari Burroughs. Sangat tidak mungkin Anda menggunakan ini. * **Sesuatu yang lain?** Berikan konteks lebih lanjut. Perangkat lunak atau sistem apa yang Anda maksud dengan "server MCP"? Apa tujuannya dalam arsitektur yang Anda inginkan? **2. Apa yang ingin Anda capai dengan USASpending.gov API?** * **Ekstraksi Data:** Apakah Anda mencoba mengunduh dataset tertentu? * **Analisis Data:** Apakah Anda mencoba melakukan perhitungan atau visualisasi pada data? * **Integrasi dengan sistem lain:** Apakah Anda mencoba memasukkan data ke aplikasi lain? * **Endpoint spesifik:** Apakah Anda tahu endpoint USASpending.gov API mana yang perlu Anda gunakan (misalnya, `/awards/`, `/transactions/`, `/references/toptier_agencies/`)? **3. Bahasa pemrograman dan alat apa yang Anda kuasai?** * **Python:** Pilihan populer untuk interaksi API dan analisis data. Pustaka seperti `requests` dan `pandas` sangat membantu. * **Java:** Bahasa umum lainnya untuk pengembangan sisi server. * **JavaScript:** Berguna untuk aplikasi front-end yang berinteraksi dengan API. * **Bahasa lain:** Beri tahu saya jika Anda menggunakan sesuatu yang lain. **Pendekatan Umum (Dengan Asumsi Server Generik):** Dengan asumsi "server MCP" mengacu pada lingkungan server generik (misalnya, server Linux yang menjalankan server web), berikut adalah garis besar umum tentang bagaimana Anda dapat berinteraksi dengan USASpending.gov API: 1. **Pilih Bahasa Pemrograman:** Pilih bahasa yang cocok untuk pengembangan sisi server dan interaksi API (misalnya, Python, Java, Node.js). 2. **Instal Pustaka yang Diperlukan:** Instal pustaka yang diperlukan untuk membuat permintaan HTTP dan memproses data JSON. Contohnya: * **Python:** `requests`, `json` * **Java:** `java.net.http`, `org.json` * **Node.js:** `node-fetch`, `axios` 3. **Tulis Kode untuk Berinteraksi dengan API:** Tulis kode untuk: * Membuat URL permintaan API (termasuk parameter yang diperlukan). * Membuat permintaan HTTP ke USASpending.gov API. * Menangani respons API (periksa kesalahan, uraikan data JSON). * Menyimpan atau memproses data sesuai kebutuhan. 4. **Deploy Kode ke "Server MCP" Anda:** Deploy kode Anda ke lingkungan server. Ini mungkin melibatkan: * Menyalin file kode ke server. * Menginstal lingkungan runtime yang diperlukan (misalnya, interpreter Python, runtime Java). * Mengonfigurasi server untuk menjalankan kode Anda (misalnya, menggunakan server web seperti Apache atau Nginx). 5. **Jadwalkan atau Picu Kode:** Tentukan bagaimana Anda ingin menjalankan kode: * **Tugas terjadwal:** Gunakan cron job atau penjadwal serupa untuk menjalankan kode secara berkala. * **Endpoint API:** Buat endpoint API di server Anda yang memicu kode saat dipanggil. **Contoh (Python):** ```python import requests import json def get_usaspending_data(endpoint, params=None): """ Mengambil data dari USASpending.gov API. Args: endpoint: Endpoint API yang akan dipanggil (misalnya, '/awards/'). params: Kamus parameter kueri. Returns: Objek JSON yang berisi respons API, atau None jika terjadi kesalahan. """ base_url = "https://api.usaspending.gov/api/v2" # Ganti dengan versi API yang benar jika diperlukan url = f"{base_url}{endpoint}" try: response = requests.get(url, params=params) response.raise_for_status() # Memunculkan pengecualian untuk kode status yang buruk return response.json() except requests.exceptions.RequestException as e: print(f"Error mengambil data: {e}") return None # Contoh penggunaan: Dapatkan 10 penghargaan terbaru awards = get_usaspending_data("/awards/", params={"limit": 10}) if awards: print(json.dumps(awards, indent=2)) # Mencetak JSON dengan format yang mudah dibaca # Proses data penghargaan di sini else: print("Gagal mengambil data penghargaan.") ``` Please provide more details about your "MCP server" and your goals, so I can give you more specific and helpful instructions.

Puppeteer MCP Server (Python Implementation)

Cermin dari

SSB-MCP

Server MCP untuk berinteraksi dengan API Statistics Norway (SSB) - memungkinkan agen AI untuk mengakses data statistik Norwegia

Eyevinn Open Source Cloud MCP Server

Cermin dari

Getting Started with Create React App

Agen Asli AI untuk Pembatasan Keamanan dan Server MCP

BirdNet-Pi MCP Server

Cermin dari

📓 GistPad MCP

📓 An MCP server for managing your personal knowledge, daily notes, and re-usable prompts via GitHub Gists

Grist MCP Server

MCP server implementation for Grist API integration

memory-mcp-server

A long-term memory storage system for LLMs using the Model Context Protocol (MCP) standard. This system helps LLMs remember the context of work done over the entire history of a project, even across multiple sessions. It uses semantic search with embeddings to provide relevant context from past interactions and development decisions.

dockerized-mcpaper-server

Mirror of

mcp-server-yahoo-finance MCP server

MCP Server for Yahoo Finance (STATUS: PRE-ALPHA)

mcp-servers

Okay, here's a breakdown of how to make an AI agent more general, along with explanations and examples: **Understanding the Goal: From Specific to Adaptable** The core idea is to move an AI agent away from being highly specialized for a single task or environment and towards being able to handle a wider range of tasks and adapt to new, unseen situations. This is often referred to as *generalization*. **Key Strategies and Techniques** 1. **Increase Data Diversity and Volume:** * **Problem:** An agent trained on a narrow dataset will likely perform poorly when faced with data outside that distribution. * **Solution:** * **Collect more data:** The more data, the better the agent can learn the underlying patterns. * **Diversify the data:** Include examples that represent the full range of possible inputs and scenarios the agent might encounter. This includes edge cases, noisy data, and variations in the environment. * **Data Augmentation:** Create synthetic data by modifying existing data (e.g., rotating images, adding noise to audio, paraphrasing text). This can artificially increase the size and diversity of the training set. * **Example:** An image recognition agent trained only on perfectly lit, front-facing photos of cats will struggle with cats in shadows, at different angles, or partially obscured. Training it on a dataset with diverse lighting, poses, and occlusions will improve its generalization. 2. **Feature Engineering and Representation Learning:** * **Problem:** The way data is represented to the agent can significantly impact its ability to generalize. Poorly chosen features can lead to overfitting or an inability to capture relevant information. * **Solution:** * **Feature Engineering:** Carefully select or create features that are relevant to the task and invariant to irrelevant variations. This often requires domain expertise. * **Representation Learning (e.g., using Neural Networks):** Allow the agent to learn its own features from the raw data. Deep learning models are particularly good at this. Techniques like autoencoders and contrastive learning can help the agent learn robust and generalizable representations. * **Example:** For a sentiment analysis task, instead of just using the raw words in a sentence, you might engineer features like the presence of certain keywords, the use of negation, or the overall sentence structure. Alternatively, you could use a pre-trained language model (like BERT or RoBERTa) to generate contextualized word embeddings, which capture semantic information. 3. **Regularization Techniques:** * **Problem:** Overfitting occurs when an agent learns the training data too well, including the noise and specific details that don't generalize to new data. * **Solution:** * **L1 and L2 Regularization:** Add penalties to the model's parameters during training to discourage overly complex models. * **Dropout:** Randomly drop out neurons during training, forcing the network to learn more robust and distributed representations. * **Early Stopping:** Monitor the agent's performance on a validation set and stop training when the performance starts to degrade, even if the training error is still decreasing. * **Example:** In a neural network, adding L2 regularization would penalize large weights, preventing the network from relying too heavily on any single feature and encouraging it to learn a more balanced representation. 4. **Transfer Learning and Fine-Tuning:** * **Problem:** Training an agent from scratch for every new task is time-consuming and requires a lot of data. * **Solution:** * **Transfer Learning:** Leverage knowledge learned from a previous task to improve performance on a new, related task. This can involve using pre-trained models or transferring learned features. * **Fine-Tuning:** Take a pre-trained model and further train it on a smaller dataset specific to the new task. This allows the agent to adapt its knowledge to the new domain. * **Example:** Instead of training an image classifier from scratch, you could use a pre-trained model like ResNet (trained on a large dataset like ImageNet) and fine-tune it on your specific image classification task. 5. **Meta-Learning (Learning to Learn):** * **Problem:** Traditional machine learning algorithms are designed to learn a single task. * **Solution:** * **Meta-Learning:** Train an agent to learn how to learn new tasks quickly and efficiently. This involves training on a distribution of tasks and learning a general learning algorithm. * **Techniques:** Model-Agnostic Meta-Learning (MAML), Reptile, and other meta-learning algorithms. * **Example:** A meta-learning agent could be trained on a variety of different classification tasks. Then, when presented with a new classification task, it can quickly learn to perform well with only a few examples. 6. **Curriculum Learning:** * **Problem:** Training an agent on a complex task from the beginning can be difficult and inefficient. * **Solution:** * **Curriculum Learning:** Gradually increase the difficulty of the training examples over time. Start with simple examples and gradually introduce more complex ones. * **Example:** When training a robot to walk, you might start by training it to stand up, then to take a few steps, and finally to walk on uneven terrain. 7. **Robustness to Noise and Adversarial Examples:** * **Problem:** AI agents can be easily fooled by noisy data or adversarial examples (inputs specifically designed to cause the agent to make mistakes). * **Solution:** * **Adversarial Training:** Train the agent on adversarial examples to make it more robust to attacks. * **Noise Injection:** Add noise to the training data to make the agent more resilient to noisy inputs. * **Defensive Distillation:** Train a new model to mimic the output of a robust model, making it more difficult to attack. * **Example:** An image classifier can be made more robust to adversarial attacks by training it on images that have been slightly perturbed to fool the original classifier. 8. **Reinforcement Learning Considerations:** * **Exploration vs. Exploitation:** In reinforcement learning, the agent needs to balance exploring the environment to discover new strategies with exploiting its current knowledge to maximize rewards. Encourage more exploration to discover more generalizable strategies. * **Reward Shaping:** Carefully design the reward function to encourage the desired behavior. Avoid reward functions that are too specific or that can be easily exploited. * **Generalization Across Environments:** Train the agent in a variety of different environments to make it more robust to changes in the environment. * **Example:** When training a robot to navigate a maze, you might give it a small reward for exploring new areas of the maze, even if it doesn't immediately lead to the goal. **Important Considerations:** * **Trade-offs:** Increasing generalization often comes at the cost of performance on the specific task the agent was originally designed for. There's a trade-off between specialization and generalization. * **Evaluation:** It's crucial to evaluate the agent's performance on a held-out test set that is representative of the real-world scenarios it will encounter. This will help you assess how well the agent is generalizing. * **Domain Knowledge:** Understanding the domain in which the agent will operate is essential for choosing the right techniques and for interpreting the results. * **Computational Resources:** Some of these techniques, such as training large neural networks, can be computationally expensive. **In Summary:** Making an AI agent more general involves a combination of techniques that aim to: * Expose the agent to a wider range of data and scenarios. * Help the agent learn more robust and generalizable representations. * Prevent the agent from overfitting to the training data. * Leverage knowledge learned from previous tasks. By carefully considering these strategies and techniques, you can create AI agents that are more adaptable, robust, and capable of handling a wider range of tasks and environments.

Okto Web3 MCP Server

MCP server menggunakan Okto V2 APIs.

MCP-Bridge

Middleware untuk menyediakan endpoint yang kompatibel dengan OpenAI yang dapat memanggil alat MCP (Management Control Plane).

MCP Google Custom Search Server

Sebuah server MCP untuk melakukan pencarian menggunakan Google Custom Search API.

arxiv-search MCP Server

Server Protokol Konteks Model untuk mencari makalah akademis di arXiv.