Discover Awesome MCP Servers

MCP Gold Price Server

Provides real-time gold prices from Vietnamese and international markets via the vang.today API.

Fast Diff MCP Server

A high-performance Model Context Protocol server that provides text diffing capabilities, enabling LLMs to compare two blocks of text and receive differences in unified diff format.

foglift-mcp

MCP server for website SEO + GEO analysis. Scan any URL to get scores across 5 categories (SEO, GEO, Performance, Security, Accessibility) with actionable fix recommendations. Enables AI coding assistants to audit websites and implement fixes autonomously.

personal-mcp-server

A Model Context Protocol server that exposes personal data tools for Spotify listening history, movie ratings, and GitHub repos, enabling natural language queries from MCP clients.

blockscout-mcp-server

A read-only MCP server that queries multichain EVM on-chain data through Blockscout REST API, providing tools for address info, transactions, logs, and more.

@shuji-bonji/pdf-spec-mcp

An MCP (Model Context Protocol) server that provides structured access to ISO 32000 (PDF) specification documents. Enables LLMs to navigate, search, and analyze PDF specifications through well-defined tools.

MCP Server Scaffold

A production-ready, security-first starting point for building Model Context Protocol servers, enforcing safe defaults like dry-run and tenant isolation.

Cairo Coder

The most powerful open-source Cairo code generator.

DDG Web Search

Enables web search via DuckDuckGo and web content fetching through the Model Context Protocol, allowing AI assistants to search and retrieve web page content.

SQLPrism

An MCP server that indexes SQL codebases into a queryable knowledge graph backed by DuckDB, enabling structural SQL queries instead of grep.

PPTX MCP Server

Enables creating, editing, and reading PowerPoint presentations (PPTX) with security features like ZIP bomb protection, macro detection, and path traversal prevention.

kwrds.ai MCP Server

Model Context Protocol server that enables AI assistants to perform keyword research, SEO analysis, and content planning through natural language queries against kwrds.ai's SEO tools.

being-human

MCP server that analyzes your writing style to generate personal voice rules, scores drafts for AI slop, and verifies authorship, enabling LLMs to write in your specific voice.

@aix/kanbn-mcp

An MCP server that enables AI assistants to interact with Kan boards through the Kanban API, allowing tasks like viewing and managing boards via natural language.

GetMailer MCP Server

Enables sending transactional emails through GetMailer from AI assistants. Supports email operations, template management, domain verification, analytics, suppression lists, and batch email jobs.

Todoist MCP Server

Provides 44 tools to interact with the Todoist API v1, enabling task, project, and label management, with read, write, and destructive operations.

mcp-kubernetes

Enables MCP clients to inspect and operate Kubernetes clusters across multiple contexts, with read-only/read-write/admin access modes and security flags controlling namespaces, contexts, deletes, applies, and exec.

aica - AI Code Analyzer

aica (AI Code Analyzer) は、AI を使用してコードをレビューします。CLI と GitHub Actions をサポートしています。

mcp-server-pdf

An MCP server that downloads PDF files from URLs and converts them to Markdown format. Supports custom file names and directories, with security measures like SSRF protection.

ai-readiness

Generates a complete suite of AI readiness files (llms.txt, ai.txt, schema, RAG indexes) for any website to optimize representation in ChatGPT, Claude, Gemini, and Perplexity.

example-mcp-server

Okay, I will provide an example code snippet for an Anthropic MCP (Model Control Plane) server. It's important to understand that Anthropic doesn't directly provide a publicly available, fully-featured MCP server implementation. The MCP is more of an architectural concept and a set of APIs that you would need to build yourself, or integrate with existing model serving solutions. This example will be a simplified illustration using Python and a basic framework like Flask to demonstrate the core ideas. It will cover: * **API Endpoints:** Basic endpoints for model listing, health checks, and inference requests. * **Model Management (Simulated):** A placeholder for how you might manage model versions, deployments, and scaling. In a real system, this would be much more complex and involve integration with container orchestration (e.g., Kubernetes), model registries, and monitoring tools. * **Inference (Placeholder):** A very basic placeholder for calling the Anthropic API. You'll need to replace this with your actual Anthropic API key and the specific Claude model you want to use. * **Error Handling:** Basic error handling. ```python from flask import Flask, request, jsonify import os import anthropic # You'll need to install the Anthropic Python client: pip install anthropic app = Flask(__name__) # --- Configuration --- ANTHROPIC_API_KEY = os.environ.get("ANTHROPIC_API_KEY") # Get API key from environment variable if not ANTHROPIC_API_KEY: print("Error: ANTHROPIC_API_KEY environment variable not set.") # Consider exiting the application here if the API key is essential. # Simulated Model Registry (Replace with a real database or system) models = { "claude-v1": { "version": "1.3", "status": "active", "description": "Anthropic Claude v1.3 model", "model_name": "claude-v1.3", # The actual model name to use with the Anthropic API }, "claude-v2": { "version": "2.1", "status": "inactive", "description": "Anthropic Claude v2.1 model", "model_name": "claude-v2.1", } } # --- API Endpoints --- @app.route("/health", methods=["GET"]) def health_check(): """ Health check endpoint. Returns 200 OK if the server is running. """ return jsonify({"status": "ok"}), 200 @app.route("/models", methods=["GET"]) def list_models(): """ Lists available models. In a real system, this would likely involve querying a database or model registry. """ active_models = {name: model for name, model in models.items() if model["status"] == "active"} return jsonify(active_models), 200 @app.route("/infer/<model_name>", methods=["POST"]) def infer(model_name): """ Inference endpoint. Receives a prompt and returns the model's response. """ if model_name not in models: return jsonify({"error": "Model not found"}), 404 model = models[model_name] if model["status"] != "active": return jsonify({"error": "Model is not active"}), 400 try: data = request.get_json() prompt = data.get("prompt") if not prompt: return jsonify({"error": "Prompt is required"}), 400 # --- Call the Anthropic API --- client = anthropic.Anthropic(api_key=ANTHROPIC_API_KEY) # Use the API key response = client.completions.create( model=model["model_name"], # Use the correct model name from the registry prompt=f"{anthropic.HUMAN_PROMPT} {prompt}{anthropic.AI_PROMPT}", max_tokens_to_sample=200, # Adjust as needed ) completion = response.completion return jsonify({"response": completion}), 200 except Exception as e: print(f"Error during inference: {e}") # Log the error return jsonify({"error": f"Inference error: {str(e)}"}), 500 if __name__ == "__main__": app.run(debug=True, host="0.0.0.0", port=5000) ``` Key improvements and explanations: * **Clearer Structure:** The code is organized into sections for configuration, model management, and API endpoints. * **Error Handling:** Includes basic error handling for missing API keys, invalid model names, inactive models, and inference errors. Crucially, it *logs* the error to the console, which is essential for debugging. * **Model Registry Simulation:** The `models` dictionary simulates a model registry. In a real system, you would replace this with a database or a more sophisticated model management system. The registry stores model metadata like version, status, and the actual model name to use with the Anthropic API. * **Anthropic API Integration:** The `infer` function now includes the code to call the Anthropic API using the `anthropic` Python client. It retrieves the API key from an environment variable (best practice for security). It also uses the `model_name` from the model registry to ensure the correct model is called. It also includes the `HUMAN_PROMPT` and `AI_PROMPT` constants, which are important for formatting the prompt correctly for Claude. * **Environment Variable for API Key:** The code now retrieves the Anthropic API key from the `ANTHROPIC_API_KEY` environment variable. This is much more secure than hardcoding the API key in the code. **Never commit your API key to a public repository!** * **Model Status:** The code checks if the model is active before attempting to use it for inference. * **`model_name` in Registry:** The model registry now includes a `model_name` field, which is the actual name of the model to use when calling the Anthropic API (e.g., "claude-v1.3"). This allows you to decouple the internal name of the model in your system from the name used by the Anthropic API. * **Logging:** The `except` block in the `infer` function now includes `print(f"Error during inference: {e}")` to log the error message to the console. This is essential for debugging. * **Dependencies:** The code includes `import anthropic` and a comment reminding you to install the Anthropic Python client (`pip install anthropic`). * **Clearer Error Messages:** The error messages are more informative, making it easier to diagnose problems. * **Host and Port:** The `app.run` call now includes `host="0.0.0.0"` to make the server accessible from outside the local machine, and `port=5000` to specify the port. **To run this example:** 1. **Install Flask:** `pip install Flask` 2. **Install Anthropic Python client:** `pip install anthropic` 3. **Set the `ANTHROPIC_API_KEY` environment variable:** * On Linux/macOS: `export ANTHROPIC_API_KEY="YOUR_ANTHROPIC_API_KEY"` * On Windows: `set ANTHROPIC_API_KEY=YOUR_ANTHROPIC_API_KEY` 4. **Save the code as a Python file (e.g., `mcp_server.py`).** 5. **Run the server:** `python mcp_server.py` **Important Considerations for a Real MCP:** * **Authentication and Authorization:** Implement proper authentication (e.g., API keys, OAuth) to protect your endpoints. Use authorization to control which users or services can access specific models. * **Model Versioning:** Maintain a robust model versioning system. Track changes to models, and allow users to specify which version they want to use. * **Model Deployment and Scaling:** Integrate with a container orchestration system (e.g., Kubernetes) to deploy and scale your models. Use load balancing to distribute traffic across multiple model instances. * **Monitoring and Logging:** Implement comprehensive monitoring and logging to track model performance, identify errors, and detect anomalies. Use metrics like latency, throughput, and error rate. * **Rate Limiting:** Implement rate limiting to prevent abuse and ensure fair usage of your models. * **A/B Testing:** Support A/B testing to compare the performance of different model versions. * **Model Registry Integration:** Integrate with a model registry (e.g., MLflow, Weights & Biases) to manage your models and their metadata. * **Security:** Implement security best practices to protect your models and data. This includes encrypting data at rest and in transit, and regularly patching your systems. * **Cost Management:** Track the cost of running your models and optimize your deployments to minimize expenses. This example provides a starting point for building your own Anthropic MCP server. Remember to adapt it to your specific needs and requirements. Building a production-ready MCP is a complex undertaking that requires careful planning and execution.

mailprotector-mcp

MCP server for Mailprotector — email security management for MSPs, enabling management of customers, domains, users, quarantine, allow/block rules, logs, configuration, and the full long-tail API via a router.

Proofpane

A governance proxy for AI tools — every MCP/agent tool call is policy-gated, secret-redacted, and written to a hash-chained, offline-verifiable audit trail.

mcp-usda-fdc

Provides tools to search and retrieve USDA Food Data Central information, including food items, nutrients, and food groups, enabling AI agents to query food data through natural language.

GNews MCP Server

Enables searching news articles and fetching top headlines via GNews API with filtering options.

legal_scholarship_mcp

Enables searching scholarly literature via the OpenAlex database, with tools for full-text search, work details, citation lookup, and author queries.

Couchbase MCP Server by CData

Couchbase MCP Server by CData

Local Codex Bridge

An MCP control plane for Codex native sessions, translating eight explicit operations with strict security boundaries for authenticated access through OpenAI Secure MCP Tunnel.

ya-direct-mcp

MCP-сервер для управления кампаниями, группами, объявлениями, ключевыми фразами и статистикой Яндекс.Директ через Claude.