Discover Awesome MCP Servers

M365 Agent MCP

Remote MCP server for ChatGPT workspace agents to access Microsoft 365 mailboxes, enabling listing, searching, reading, and sending emails with per-agent mailbox isolation.

Advocu MCP Server

Enables Google Developer Experts, Docker Captains, and Microsoft MVPs to submit professional activity reports via conversational AI, with support for multiple programs and rate-limited API access.

PinterestMCP

Read-only MCP server for exposing Pinterest boards, sections, pins, and imagery as a visual reference library. Enables ChatGPT and other clients to list, search, and retrieve Pinterest content through natural language.

1C MCP Toolkit

Integrates AI agents with 1C:Enterprise databases via MCP and REST API, supporting a built-in HTTP server (no Python required) or a Python proxy mode.

DevPulse PM Agent

Gives Claude four decision tools for product management: rank backlog, mine customer feedback, size sprint capacity, and trace dependency risk, all grounded in JSON data.

legal-doc-intelligence

MCP server that analyzes legal documents, extracts key clauses, identifies risks, and summarizes contracts. 8 tools for AI agents needing legal document intelligence.

Postgres MCP Pro

An open-source MCP server that provides AI agents with advanced PostgreSQL capabilities including index tuning, query plan optimization, and comprehensive database health analysis. It supports safe SQL execution through configurable access modes and offers both stdio and SSE transport options for various development environments.

agent-fact-system

Local-first knowledge system for reasoning agents, exposing facts, evidence, documents, retrieval, and audit history through a thin stdio MCP server.

Azure AI Foundry MCP Server

Enables interaction with Azure AI Foundry services through a unified interface for model exploration and deployment, knowledge indexing and search, AI evaluation, and fine-tuning operations. Supports both GitHub token-based model testing and full Azure deployment workflows.

buffer-mcp

MCP server for Buffer social media scheduling via the GraphQL API, enabling post creation, queue management, engagement metrics, and media uploads.

agent-guard-mcp

agent-guard-mcp

opencode-vision-mcp

MCP server for image recognition via OpenRouter AI. It sends an image to a primary model (fast) and falls back to a secondary model if needed, returning a textual description.

Imagine if you could turn an LLM into a simulator

AgentTorch MCP Server - Bayangkan jika model Anda dapat melakukan simulasi.

minimax-coding-plan-mcp

Node.js MCP server for MiniMax's Token Plan, providing image understanding and web search capabilities.

Lab Registry Server

Enables MCP clients to discover and fetch skills, agents, commands, and hooks from the Gen-e2 Lab Registry, and check local inventory compliance against the registry.

remember-mcp

Multi-tenant memory system MCP server with vector search, relationships, and trust-based access control for AI assistants.

MCP Chat

A command-line interface application that enables interaction with LLMs through document retrieval, command-based prompts, and extensible tool integrations using the Model Control Protocol architecture.

DevContext

Workspace-aware MCP server that provides AI clients with structural code understanding via AST parsing, hybrid retrieval, and git history, enabling accurate code search, definition lookup, and blame analysis.

gleif-mcp-server

A Model Context Protocol server that provides access to the GLEIF REST API for querying legal entity information, LEI records, issuer details, and organizational relationships.

Weather MCP Server

Provides current weather data and city comparisons for any location with support for metric/imperial units and optional forecasts.

nova-act-mcp

Sebuah server MCP yang menyediakan alat untuk mengendalikan peramban web menggunakan Amazon Nova Act SDK. Memungkinkan alur kerja otomatisasi peramban multi-langkah melalui agen MCP.

Image Generator

I understand you want me to generate and return an image using Together.ai. However, I am a text-based AI and do not have the capability to directly generate or return images. I can provide you with the necessary information and code snippets to do so yourself using the Together.ai API. To generate an image using Together.ai, you would typically need to: 1. **Sign up for a Together.ai account and obtain an API key.** This is essential for authenticating your requests. 2. **Choose a model.** Together.ai offers various image generation models. You'll need to select one that suits your needs. 3. **Use the Together.ai API to send a request with your desired parameters.** This includes the model you want to use, the prompt describing the image you want to generate, and any other relevant settings (e.g., image size, number of images). 4. **Receive the generated image data from the API.** This data is usually in the form of a URL pointing to the image or a base64 encoded string. 5. **Display or save the image.** You can then display the image in your application or save it to a file. Here's a basic example of how you might use the Together.ai API with Python (using the `requests` library): ```python import requests import json # Replace with your actual API key api_key = "YOUR_TOGETHERAI_API_KEY" # API endpoint for image generation api_url = "https://api.together.xyz/inference" # Request payload payload = { "model": "stabilityai/stable-diffusion-xl-base-1.0", # Example model "prompt": "A futuristic cityscape at sunset", "n_images": 1, # Number of images to generate "size": "512x512", # Image size "steps": 30 # Number of steps } headers = { "Authorization": f"Bearer {api_key}", "Content-Type": "application/json" } try: response = requests.post(api_url, headers=headers, data=json.dumps(payload)) response.raise_for_status() # Raise HTTPError for bad responses (4xx or 5xx) data = response.json() # Check for errors in the response if "error" in data: print(f"Error from Together.ai: {data['error']}") else: # Assuming the API returns a URL to the generated image image_url = data["output"]["choices"][0]["image_url"] print(f"Image URL: {image_url}") # You can then use this URL to display or download the image # For example, to download the image: image_response = requests.get(image_url, stream=True) image_response.raise_for_status() with open("generated_image.png", "wb") as out_file: for chunk in image_response.iter_content(chunk_size=8192): out_file.write(chunk) print("Image downloaded successfully!") except requests.exceptions.RequestException as e: print(f"Request failed: {e}") except json.JSONDecodeError: print("Failed to decode JSON response.") except KeyError as e: print(f"Missing key in JSON response: {e}") except Exception as e: print(f"An unexpected error occurred: {e}") ``` **Important Notes:** * **Replace `"YOUR_TOGETHERAI_API_KEY"` with your actual API key.** * **Choose the appropriate model.** The example uses `stabilityai/stable-diffusion-xl-base-1.0`. Refer to the Together.ai documentation for a list of available models and their capabilities. * **Adjust the `prompt` and other parameters** in the `payload` to customize the image generation. * **Error Handling:** The code includes basic error handling to catch potential issues with the API request or response. You should implement more robust error handling in a production environment. * **Rate Limits:** Be aware of Together.ai's rate limits and usage policies. * **API Changes:** The Together.ai API may change over time. Always refer to the official documentation for the most up-to-date information. This code provides a starting point. You'll need to adapt it to your specific needs and integrate it into your application. Remember to consult the Together.ai documentation for detailed information on their API and available models. I can help you refine the prompt, choose a model, or troubleshoot any issues you encounter while implementing this. Just let me know what you need! **Indonesian Translation:** Saya mengerti Anda ingin saya menghasilkan dan mengembalikan gambar menggunakan Together.ai. Namun, saya adalah AI berbasis teks dan tidak memiliki kemampuan untuk menghasilkan atau mengembalikan gambar secara langsung. Saya dapat memberi Anda informasi dan cuplikan kode yang diperlukan untuk melakukannya sendiri menggunakan API Together.ai. Untuk menghasilkan gambar menggunakan Together.ai, Anda biasanya perlu: 1. **Mendaftar akun Together.ai dan mendapatkan kunci API.** Ini penting untuk mengotentikasi permintaan Anda. 2. **Pilih model.** Together.ai menawarkan berbagai model pembuatan gambar. Anda perlu memilih salah satu yang sesuai dengan kebutuhan Anda. 3. **Gunakan API Together.ai untuk mengirim permintaan dengan parameter yang Anda inginkan.** Ini termasuk model yang ingin Anda gunakan, perintah yang menjelaskan gambar yang ingin Anda hasilkan, dan pengaturan relevan lainnya (misalnya, ukuran gambar, jumlah gambar). 4. **Menerima data gambar yang dihasilkan dari API.** Data ini biasanya berupa URL yang menunjuk ke gambar atau string yang dikodekan base64. 5. **Menampilkan atau menyimpan gambar.** Anda kemudian dapat menampilkan gambar di aplikasi Anda atau menyimpannya ke file. Berikut adalah contoh dasar bagaimana Anda dapat menggunakan API Together.ai dengan Python (menggunakan pustaka `requests`): ```python import requests import json # Ganti dengan kunci API Anda yang sebenarnya api_key = "KUNCI_API_TOGETHERAI_ANDA" # Endpoint API untuk pembuatan gambar api_url = "https://api.together.xyz/inference" # Payload permintaan payload = { "model": "stabilityai/stable-diffusion-xl-base-1.0", # Contoh model "prompt": "Pemandangan kota futuristik saat matahari terbenam", "n_images": 1, # Jumlah gambar yang akan dihasilkan "size": "512x512", # Ukuran gambar "steps": 30 # Jumlah langkah } headers = { "Authorization": f"Bearer {api_key}", "Content-Type": "application/json" } try: response = requests.post(api_url, headers=headers, data=json.dumps(payload)) response.raise_for_status() # Munculkan HTTPError untuk respons buruk (4xx atau 5xx) data = response.json() # Periksa kesalahan dalam respons if "error" in data: print(f"Kesalahan dari Together.ai: {data['error']}") else: # Asumsikan API mengembalikan URL ke gambar yang dihasilkan image_url = data["output"]["choices"][0]["image_url"] print(f"URL Gambar: {image_url}") # Anda kemudian dapat menggunakan URL ini untuk menampilkan atau mengunduh gambar # Misalnya, untuk mengunduh gambar: image_response = requests.get(image_url, stream=True) image_response.raise_for_status() with open("gambar_yang_dihasilkan.png", "wb") as out_file: for chunk in image_response.iter_content(chunk_size=8192): out_file.write(chunk) print("Gambar berhasil diunduh!") except requests.exceptions.RequestException as e: print(f"Permintaan gagal: {e}") except json.JSONDecodeError: print("Gagal mendekode respons JSON.") except KeyError as e: print(f"Kunci hilang dalam respons JSON: {e}") except Exception as e: print(f"Terjadi kesalahan tak terduga: {e}") ``` **Catatan Penting:** * **Ganti `"KUNCI_API_TOGETHERAI_ANDA"` dengan kunci API Anda yang sebenarnya.** * **Pilih model yang sesuai.** Contohnya menggunakan `stabilityai/stable-diffusion-xl-base-1.0`. Lihat dokumentasi Together.ai untuk daftar model yang tersedia dan kemampuannya. * **Sesuaikan `prompt` dan parameter lainnya** di `payload` untuk menyesuaikan pembuatan gambar. * **Penanganan Kesalahan:** Kode menyertakan penanganan kesalahan dasar untuk menangkap potensi masalah dengan permintaan atau respons API. Anda harus menerapkan penanganan kesalahan yang lebih kuat di lingkungan produksi. * **Batas Kecepatan:** Waspadai batas kecepatan dan kebijakan penggunaan Together.ai. * **Perubahan API:** API Together.ai dapat berubah dari waktu ke waktu. Selalu lihat dokumentasi resmi untuk informasi terbaru. Kode ini menyediakan titik awal. Anda perlu menyesuaikannya dengan kebutuhan spesifik Anda dan mengintegrasikannya ke dalam aplikasi Anda. Ingatlah untuk berkonsultasi dengan dokumentasi Together.ai untuk informasi rinci tentang API mereka dan model yang tersedia. Saya dapat membantu Anda menyempurnakan perintah, memilih model, atau memecahkan masalah apa pun yang Anda temui saat menerapkan ini. Beri tahu saya apa yang Anda butuhkan!

Directory Explorer MCP Server

A Model Context Protocol server that provides token-aware directory exploration and file analysis for Large Language Models, enabling intelligent codebase navigation with features like directory scanning, file content extraction, and token usage statistics.

EGH Research MCP Server

Provides offline research and advanced search capabilities for Ellen Gould Harmon's writings via MCP and HTTP APIs, including PDF generation and Docker deployment.

mcp-arcgis-chestercounty

Enables querying Chester County, PA open geospatial data via ArcGIS, including search, layer query, and schema retrieval.

hass-mcp-server

MCP server for full Home Assistant control, enabling AI agents to manage dashboards, automations, files, apps, entities, and more via REST API, WebSocket, and SSH.

litellm-mcp

MCP server that provides tools to interact with the LiteLLM proxy API, enabling LLM completions, embeddings, image generation, and admin operations.

linux-mcp-server

Dukungan untuk menjalankan shell di Linux.

Monad NFT Launch Tool

An MCP server that helps users create NFT collections, deploy smart contracts to the Monad blockchain, and generate mint websites with Claude AI integration.

Chromadb Fastapi Mcp

Saya akan menerjemahkan frasa "chromadb を fastapi 化し fastapi-mcp で mcp server として利用" ke dalam bahasa Indonesia. Terjemahan: **"Mengubah ChromaDB menjadi aplikasi FastAPI dan menggunakannya sebagai server MCP dengan FastAPI-MCP."** Berikut adalah sedikit penjelasan tambahan untuk memperjelas terjemahannya: * **Mengubah ChromaDB menjadi aplikasi FastAPI:** Ini berarti membungkus fungsionalitas ChromaDB dalam sebuah API (Application Programming Interface) menggunakan framework FastAPI. * **Server MCP dengan FastAPI-MCP:** MCP kemungkinan besar adalah singkatan dari "Microservice Control Plane". FastAPI-MCP adalah library atau framework yang digunakan untuk mengelola dan mengontrol microservice yang dibangun dengan FastAPI. Jadi, menggunakan ChromaDB yang sudah di-FastAPI-kan sebagai server MCP berarti menggunakannya sebagai bagian dari arsitektur microservice yang dikelola oleh FastAPI-MCP. Semoga terjemahan ini membantu!