Discover Awesome MCP Servers

WHOOP MCP Server for Poke

Connects WHOOP fitness data to Poke AI assistant, enabling natural language queries for recovery scores, sleep analysis, strain tracking, and healthspan metrics.

Conductor

Provides a persistent hierarchical task tree for LLM agents, enabling them to decompose work, track progress, record results, and handle failures outside the context window, with an optional web UI for monitoring and control.

After Effects Motion Control Panel

A robust system that connects web UI to After Effects, enabling real-time command processing and monitoring with comprehensive error handling.

PixelLabRat

MCP server for generating style-consistent pixel art assets from PixelLab API, with project management, asset review, and an embedded Claude assistant.

SQD Portal MCP Server

Thin MCP wrapper around the SQD Portal API for blockchain data queries across multiple networks including EVM, Solana, Bitcoin, Substrate, and Hyperliquid. Provides 25 public tools for discovery, cross-chain queries, and chain-specific operations.

odoo19-mcp-server

MCP Server for Odoo 19 using JSON-2 API, built with FastMCP

YouTube MCP

Enables searching for songs on YouTube and automatically playing them in a web browser using the official YouTube Data API v3. It supports cross-platform execution on Windows, macOS, and Linux with built-in input validation.

tesla-powerwall

Enables AI assistants to monitor and control Tesla Powerwall 2 systems via local gateway API.

Brand Intelligence MCP

Provides domain and brand intelligence for AI agents, including company enrichment, tech stack detection, and brand research from free public sources with an on-demand cache.

Interactive Clarify

A universal 'Ask User Questions' MCP tool for AI coding agents.

Selenium MCP Server

A server implementation that enables controlling web browsers programmatically through Claude's desktop application, providing comprehensive Selenium WebDriver operations for browser automation with Chrome and Firefox support.

rippr

Extract YouTube transcripts for AI agents, RAG pipelines, and LLM workflows. Supports any YouTube URL. Returns clean text or timestamped segments. No API keys required.

Custom Figma MCP

Local bridge enabling AI agents to inspect and edit the currently open Figma Desktop file through the Figma Plugin API.

Agentic-AI-Planning-And-Reasoning-MCP

MCP server for step-by-step mathematical reasoning and planning, enabling AI agents to execute calculations and perform GUI actions like opening PowerPoint.

mcp-bible

MCP server for Bible study, providing multi-version verse lookup, keyword/semantic search, cross-references, and word studies with original language and lexicon details.

Jira Service Management MCP Server

Enables configuration of Jira Service Management Cloud via natural language, supporting request types, custom fields, forms, and more.

ArcRift MCP Server

Persistent memory for AI coding tools that captures conversations, builds a searchable knowledge graph, and automatically injects relevant context into new prompts.

sse-email-mcp-server

Provides email sending and receiving via SMTP/IMAP/POP3, supporting major email providers and dynamic authentication for AI assistant integration.

SFCC Development MCP Server

Provides comprehensive access to Salesforce B2C Commerce Cloud development tools including SFCC API documentation, best practices guides, log analysis, and system object definitions. Enables AI assistants to help with SFCC development tasks through both documentation-only mode and full credential-based mode.

LinkedIn MCP

Enables AI assistants to access and interact with LinkedIn data—profiles, messaging, jobs, companies, and more—via MCP, with remote or local deployment.

Local Scanner MCP Server

Here are a few options for an MCP (Malware Configuration Parser) server that can scan local code and localhost URLs, along with considerations for each: **1. Using Existing Malware Analysis Sandboxes (with API access):** * **Concept:** Leverage established online sandboxes that offer API access. You'd submit your local code or URLs to the sandbox via its API, and it would perform the analysis and return the results. This is often the most practical approach because it avoids the complexity of setting up and maintaining your own full-fledged sandbox. * **Examples:** * **VirusTotal:** A very popular and free (with limitations) service. It aggregates results from many different antivirus engines. Excellent for a quick check. The API has rate limits, so it's not ideal for high-volume scanning without a paid subscription. * **Hybrid Analysis (Falcon Sandbox):** A more advanced sandbox that provides detailed behavioral analysis reports. It has a free tier with limitations and paid options for more features and higher usage. * **ANY.RUN:** An interactive online sandbox that allows you to observe malware execution in real-time. It has a free tier and paid options. * **Joe Sandbox Cloud:** A commercial sandbox with a wide range of analysis capabilities. * **Implementation:** 1. **Choose a Sandbox:** Select a sandbox that meets your needs in terms of features, pricing, and API access. 2. **Obtain API Key:** Register for an account and obtain an API key. 3. **Write a Script/Application:** Develop a script (e.g., in Python) or application that: * Reads the local code or URL. * Uses the sandbox's API to submit the code/URL for analysis. * Parses the API response to extract the relevant information (e.g., detected malware, behavioral indicators). * Presents the results to the user. * **Pros:** * Relatively easy to set up. * Leverages the expertise and resources of established security vendors. * Access to a wide range of analysis tools and techniques. * Often provides detailed reports. * **Cons:** * Requires an internet connection. * May have rate limits or usage restrictions (especially with free tiers). * You are trusting a third party with your code/URLs (consider privacy implications). * API changes can break your integration. **2. Using Open-Source Malware Analysis Tools (Local Installation):** * **Concept:** Install open-source malware analysis tools on your own server. This gives you more control but requires significantly more effort to set up and maintain. * **Examples:** * **Cuckoo Sandbox:** A popular open-source automated malware analysis system. It runs malware in a virtualized environment and records its behavior. Requires significant setup and configuration. * **YARA:** A pattern-matching tool that can be used to identify malware based on rules. You'll need to create or find YARA rules relevant to the types of malware you're looking for. * **ClamAV:** An open-source antivirus engine. Can be used for basic malware detection. * **Radare2:** A reverse engineering framework that can be used to analyze malware. Very powerful but has a steep learning curve. * **Implementation:** 1. **Choose Tools:** Select the tools that best fit your needs. Cuckoo Sandbox is a good starting point for comprehensive analysis. 2. **Install and Configure:** Follow the installation instructions for each tool. This can be complex, especially for Cuckoo Sandbox. You'll need to set up virtual machines, networking, and other dependencies. 3. **Develop a Script/Application:** Write a script or application that: * Reads the local code or URL. * Submits the code/URL to the analysis tools. * Parses the output of the tools to extract the relevant information. * Presents the results to the user. * **Pros:** * More control over the analysis environment. * No reliance on third-party services. * Can be used offline. * Potentially more privacy. * **Cons:** * Significantly more complex to set up and maintain. * Requires a good understanding of malware analysis techniques. * Requires more resources (hardware, time, expertise). * You are responsible for keeping the tools up-to-date and secure. * May require creating your own malware signatures or rules. **3. Simplified Local Scanning (Basic):** * **Concept:** Use simpler tools for basic scanning, such as file hashing and string searching. This is not a full-fledged MCP server but can be useful for identifying known malicious files or patterns. * **Examples:** * **Hashing:** Calculate the MD5, SHA-1, or SHA-256 hash of the file and compare it to known malware hashes (e.g., from VirusTotal's database). * **String Searching:** Search for suspicious strings in the code, such as URLs, IP addresses, or function names associated with malware. * **Regular Expressions:** Use regular expressions to identify patterns that might indicate malicious code. * **Implementation:** 1. **Write a Script/Application:** Develop a script or application that: * Reads the local code or URL. * Calculates the hash of the file. * Searches for suspicious strings or patterns. * Presents the results to the user. * **Pros:** * Simple to implement. * Fast. * Can be used offline. * **Cons:** * Limited detection capabilities. * Easily bypassed by malware authors. * High false positive rate. **Important Considerations:** * **Security:** If you are running malware analysis tools on your own server, it is crucial to isolate the environment to prevent malware from escaping and infecting your system. Use virtualization, sandboxing, and network segmentation. * **Privacy:** Be careful about submitting sensitive code or URLs to third-party services. Consider the privacy implications and choose services that have a good reputation for data security. * **False Positives:** Malware analysis tools can sometimes produce false positives. It is important to carefully review the results and investigate any suspicious findings. * **Updates:** Keep your malware analysis tools and signature databases up-to-date to ensure that they can detect the latest threats. * **Legal Issues:** Be aware of any legal restrictions on analyzing malware. In some jurisdictions, it may be illegal to possess or analyze malware without authorization. **Example (Python using VirusTotal API - Basic):** ```python import requests import hashlib import os def scan_file_with_virustotal(file_path, api_key): """Scans a file with VirusTotal using its API.""" if not os.path.exists(file_path): print(f"Error: File not found: {file_path}") return try: with open(file_path, "rb") as f: file_content = f.read() file_hash = hashlib.sha256(file_content).hexdigest() url = "https://www.virustotal.com/api/v3/files" headers = {"x-apikey": api_key} files = {"file": (os.path.basename(file_path), file_content)} response = requests.post(url, headers=headers, files=files) if response.status_code == 200: analysis_id = response.json()['data']['id'] print(f"File uploaded. Analysis ID: {analysis_id}") # Poll for results (you might need to wait a few minutes) analysis_url = f"https://www.virustotal.com/api/v3/analyses/{analysis_id}" analysis_response = requests.get(analysis_url, headers=headers) if analysis_response.status_code == 200: analysis_data = analysis_response.json()['data']['attributes']['stats'] print("Analysis Results:") print(f" Detected: {analysis_data['malicious']}") print(f" Undetected: {analysis_data['undetected']}") print(f" Harmless: {analysis_data['harmless']}") print(f" Suspicious: {analysis_data['suspicious']}") else: print(f"Error getting analysis results: {analysis_response.status_code} - {analysis_response.text}") else: print(f"Error uploading file: {response.status_code} - {response.text}") except Exception as e: print(f"An error occurred: {e}") if __name__ == "__main__": file_to_scan = "path/to/your/file.exe" # Replace with the actual path to your file virustotal_api_key = "YOUR_VIRUSTOTAL_API_KEY" # Replace with your VirusTotal API key scan_file_with_virustotal(file_to_scan, virustotal_api_key) ``` **Explanation of the Python example:** 1. **Imports:** Imports necessary libraries (requests for making HTTP requests, hashlib for calculating file hashes, and os for file operations). 2. **`scan_file_with_virustotal` function:** * Takes the file path and VirusTotal API key as input. * Reads the file content in binary mode (`"rb"`). * Calculates the SHA-256 hash of the file. * Constructs the API request to upload the file to VirusTotal. * Sends the request using `requests.post`. * Parses the JSON response to get the analysis ID. * Polls the VirusTotal API to get the analysis results. * Prints the detection statistics (malicious, undetected, harmless, suspicious). * Handles potential errors. 3. **`if __name__ == "__main__":` block:** * Sets the `file_to_scan` and `virustotal_api_key` variables. **You must replace these with your actual file path and API key.** * Calls the `scan_file_with_virustotal` function to scan the file. **To use this example:** 1. **Install `requests`:** `pip install requests` 2. **Get a VirusTotal API Key:** Sign up for a free account on VirusTotal ([https://www.virustotal.com/](https://www.virustotal.com/)) and obtain an API key. 3. **Replace Placeholders:** Replace `"path/to/your/file.exe"` and `"YOUR_VIRUSTOTAL_API_KEY"` with the actual values. 4. **Run the Script:** Execute the Python script. This is a basic example. You can extend it to handle URLs, process the analysis results in more detail, and integrate it into a larger application. Remember to handle errors and rate limits appropriately. **For scanning localhost URLs:** The approach is similar to scanning local files, but instead of reading a file, you would make an HTTP request to the localhost URL and analyze the response. You could use the `requests` library in Python to make the HTTP request and then analyze the HTML or JavaScript code in the response for suspicious patterns. You could also use a headless browser like Puppeteer or Selenium to render the page and analyze the rendered content. Be very careful when visiting localhost URLs, as they could potentially execute malicious code on your system. Choose the option that best suits your needs and technical expertise. For most use cases, using an existing malware analysis sandbox with API access is the most practical and efficient approach. Remember to prioritize security and privacy when handling potentially malicious code.

memdb

A SQLite-backed MCP memory server providing persistent memory storage with full-text search and knowledge graph capabilities for AI assistants.

Browser MCP Server

Enables AI assistants to automate web browsers through Playwright, providing capabilities for navigation, content extraction, form filling, screenshot capture, and JavaScript execution. Supports multiple browser engines with comprehensive error handling and security features.

Excalidraw MCP Server

Enables AI agents to create, modify, and share diagrams on a live Excalidraw canvas through MCP tools, supporting shapes, text, arrows, batch operations, and export to shareable links with images.

e2e-mcp-test

An end-to-end test MCP server built with FastMCP that exposes a REST API as a set of tools for AI agents. It enables LLMs to perform CRUD operations on an upstream API by mapping HTTP methods to MCP tools.

book-mcp

A service that lets readers chat with fictional characters from novels, where the AI adopts the character's personality, memory, and knowledge for immersive roleplay.

Zendesk MCP Server

A server implementation that provides Claude AI with the ability to interact with Zendesk ticketing systems through various functions including retrieving, searching, creating, and updating tickets.

reflens

An MCP server that indexes reference repositories and provides tools for AI coding agents to retrieve lossless code context, enabling reasoning over codebases larger than the agent's context window.

Writespace

Persistent docs and memory for AI agents. Writespace is a collaborative markdown editor with a built-in MCP server — your model reads, writes, organizes, and searches a shared workspace while humans edit the same docs live. Drop the ranked full-text search straight in as RAG retrieval.