"Information about Home Assistant software or devices" matching MCP servers:

Pinecone Assistant MCP server

MCP server for querying your local Google Takeout activity (Search/YouTube history) via SQLite/FTS5. Provides tools for keyword search, activity stats, and database info, enabling AI assistants to cite your personal history.

Enables MCP clients to ask natural-language questions over GitHub docs and code, retrieving permission-filtered context through hybrid search and reranking and returning cited answers with GitHub permalinks. It also redacts secrets/PII before indexing and records audit events for who saw what.

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

A read-only MCP server that enables AI clients to search a knowledge base and retrieve complete source documents via narrow search and fetch tools.

Enables interaction with OpenAI's Chat Completion and Assistants APIs, supporting assistant management, file operations, and direct queries to GPT models through standardized MCP tools.

Enables querying, listing, and summarizing personal knowledge base documents using RAG with hybrid search and LLM.

MCP server that allows AI agents to read, search, summarize, and answer questions about local PDF, DOCX, XLSX, and TXT files through five tools.

Enables AI-powered medical information retrieval through FHIR clinical document search and GraphRAG-based exploration of medical entities and relationships. Combines vector search with knowledge graph queries for comprehensive healthcare data analysis.

Enables AI-powered interaction with Metabase instances and PostgreSQL databases through natural language. Creates models, SQL queries, metrics, and dashboards using both Metabase API and direct database connections.

Provides medical evidence tools including PubMed search, citation verification, clinical trial lookup, drug information, drug interaction checking, PICO extraction, and medical entity recognition via MCP.

Enables chat, document search (RAG), and a declarative SQL tool builder over MCP so any client can use these capabilities.

Enables local document Q&A by reading .txt or .pdf files and answering questions in Persian using locally running models.

It lets MCP clients such as Claude Desktop ask natural-language questions about the Model Context Protocol and get grounded answers with reranking, semantic caching, guardrails, PII masking, and hallucination detection.

Hybrid RAG pipeline that indexes documents and exposes them via an MCP server, enabling natural language queries to retrieve relevant context chunks for LLMs.

MCP server that indexes your Obsidian notes into a Milvus vector database and enables querying them via a local or OpenAI LLM, with real-time synchronization.

Enables MCP clients to query a local Kubernetes/Docker knowledge base through semantic search, ask DevOps questions via a RAG pipeline, and search a troubleshooting journal by symptom.

MCP server for Topaz switches: searches documentation, performs network diagnostics (ping, traceroute, port scanning, etc.), calculates subnets, and generates VLAN/base configurations. Also includes a web UI for use without an MCP client.

MCP server that provides 8 local RAG tools using LlamaIndex and Ollama, enabling AI-powered document querying, summarization, analysis, and comparison over PDFs, DOCX, XLSX, and CSV files.

A custom MCP server providing semantic note memory (Qdrant + FastEmbed) and optional web search (Tavily) tools for a LangGraph ReAct agent.