"author:psyb0t" matching MCP servers:

MCP server for predictalot, providing streamable HTTP tools for zero-shot time-series forecasting with multiple foundation models and per-type ensembles. Tabular ML endpoints are currently HTTP-only.

Enables local typed decision-making over MCP Streamable HTTP, running Laya and Von models to turn arbitrary state into choice, score, and yes/no answers with probabilities.

Unified email access via IMAP/SMTP, enabling reading, searching, sending, and deleting messages across multiple accounts through a single MCP server.

Enables on-demand OHLC bar analysis with configurable technical indicators and smart-money concepts, returning only the requested primitives via stateless HTTP or MCP.

Enables LLM agents to drive a self-hosted video toolkit through MCP tools, including lipsync, face restoration, ffmpeg operations, and metadata retrieval.

Exposes a Telegram user account via MCP, enabling AI agents to send, read, and manage messages, chats, and media using full MTProto access through Telethon. It wraps Telethon behind a JSON HTTP API and MCP endpoint, allowing agents to interact with Telegram as the authenticated user.

Unifies Google Search Console, Bing Webmaster Tools, GA4, and PageSpeed APIs behind one MCP server, letting an agent join search, indexing, and analytics data across providers while staying read-only and boundary-limited by default.

Enables AI agents to control a stealthy browser via the Model Context Protocol, supporting navigation, screenshots, clicking, typing, and more.

Enables AI agents to perform comprehensive audio processing—stem separation, analysis, transcription, restoration, speech processing, and generation—through a unified self-hosted API with asynchronous jobs and webhooks.