Encoding

The Pearl MCP Server expands the ecosystem of MCP-compatible tools by introducing a distinctive type of tool: humans. Unlike traditional MCP implementations that connect to APIs or code snippets, this server enables AI agents (e.g., Claude, Cursor, GitHub Copilot) to interact with domain-specific human experts in real time. It offers a robust path for tasks that require nuanced judgment, contextual understanding, or legal, medical, and technical advice from certified professionals.

Extracts transcripts from YouTube videos using various URL formats, enabling automated content analysis and summarization.

MCP server built on FastMCP with 3 core services: ScrapeCreators API (Google Ads Transparency), SQLite media cache, & Gemini AI for video analysis. Exposes 7 tools for ad search, retrieval, AI media analysis & cache mgmt. Uses intelligent caching in ~/.cache/google-ads-mcp/ to avoid redundant calls. Handles images (Claude vision) & videos (Gemini) with full error handling.

Interact seamlessly with the Bybit API to fetch market data, manage your account, and execute trades. Leverage powerful tools to enhance your trading experience and automate your strategies effortlessly. If you wish to use an API key restricted to your personal IP address, you must configure the MCP server using Docker. Please refer to the README.md file in the GitHub repository for guidelines.

Integrates with MySQL databases to enable read-only schema inspection and query execution, ensuring data integrity and security for analytical applications.

Transforms stdio-based MCP servers into websocket-accessible servers, enabling network-based communication and simplified client development.