"Home Assistant integration with Codex or ChatGPT" matching MCP servers:

Enables Claude Code to query ChatGPT for second opinions and compare responses between models.

Enables Codex to delegate deep research, PRD drafting, design thinking, and current-information lookups to ChatGPT Web/App via a local MCP connector, saving Markdown results to the filesystem.

MCP server that lets any LLM client query the Home Credit Default Risk SQLite database (307,511 loan applications) through 7 read-only tools, 4 resources, and 1 prompt over stdio, with natural language, SQL, and tool-calling interfaces.

MCP server for IG's REST Trading API and Lightstreamer streaming API. Provides tools for accounts, markets, positions, orders, watchlists, sentiment, OTC trades, and streaming price/account/trade/chart data.

Enables natural language control of quantum photonics experiments through the qudi framework. Supports safe instrument control, measurement execution, and safety system management with built-in runlevel protection and parameter validation.

Enables querying Google NotebookLM notebooks directly from Claude Desktop (MCP) and Claude Code (CLI), providing citation-backed answers from Gemini.

Enables querying the Codex General Standard for Food Additives to check whether an additive is permitted in a food category, at what maximum level or GMP, and under which conditions.

Enables retrieval of Codex Alimentarius maximum levels for food contaminants and toxins, filtered by contaminant or commodity, with source PDF page references.

Enables Codex to interact with Google NotebookLM, allowing it to list notebooks, add sources, ask questions, and generate audio overviews.

An MCP server that enables saving, retrieving, and managing research content using ChromaDB vector storage and semantic search.

A local MCP server for reviewing student housing form submissions, supporting listing, validation, duplicate detection, summarization, and data extraction with optional AI analysis.

A research assistant server that enables saving, organizing, and retrieving research content with semantic search using ChromaDB and OpenAI embeddings.

Provides access to FluentLab's funding database, enabling users to search for funding opportunities and retrieve document checklists required for specific funding programme applications.

Enables AI assistants to query ClinicalTrials.gov and PubMed for research evidence, and to compare regulatory document changes against internal files, with strict read-only access and no ability to modify or export data.

Combines YouTube subtitle extraction, Wikipedia concept lookup, and arXiv paper search into one pipeline without any API keys, enabling generation of comprehensive study notes from a single YouTube URL.

Provides access to Codex Alimentarius maximum residue limits, enabling searches for pesticide and veterinary drug limits by substance or food commodity, including adoption status and JECFA cross-references.

A custom MCP server that enables AI assistants to perform comprehensive research tasks, including searching ArXiv, summarizing papers via Groq, managing local research notes, and pushing findings to GitHub.

A Zotero library management MCP server designed for Cloudflare Workers that enables searching, reading, and writing library items. It allows users to manage metadata, full-text content, and attachments through natural language interactions.

Enables AI clients to read PDFs and selections from Zotero, edit Better Notes in real time, and synchronize Markdown notes.

A persistent MCP-to-ACP bridge that lets a Codex-led controller delegate research tasks to DeepSeek Harness for derivation, computation, and file work, while recording tasks, sessions, routing, and result evidence. It supports idempotent tasks, clarification follow-ups, session resume, model routing, and bounded recovery, with approvals relayed back to the controller.