"Proton Mail" matching MCP servers:

A brain for your mail: MailFathom turns IMAP mailboxes into a self-hosted, AI-native service.

Provides cited retrieval over local-first knowledge sources (TXT, CSV, Google Sheets, Zoho Mail, MBOX) via SQLite FTS5, with tools for searching and checking source status, returning evidence links instead of generated answers.

A Python-based MCP server that enables document-based question answering by processing PDF, TXT, and Markdown files through OpenAI's API. It provides hallucination-free responses based strictly on document content using semantic search and includes a web interface for management.

Personal digital memory: a desktop app that indexes your mail, chats, and documents into a local SQLite corpus on your machine — parsing and OCR run on-device via llama.cpp — and serves them to any MCP client. Local server on 127.0.0.1, plus an optional per-user remote endpoint (you.localkiagent.com) whose TLS terminates on your own device.

Enables document-based question answering using OpenAI's GPT-4 with semantic search and embeddings. Upload PDF, TXT, or Markdown files and get answers strictly based on document content with source attribution and confidence scores.

Enables natural language management of Hammerspace storage clusters with automated file ingestion, tagging, tier management, and vector embedding generation. Supports real-time file monitoring, multi-format document processing, and Kubernetes-based ingestion workflows with Milvus integration.

Enables MCP clients to store and retrieve user preferences, behaviors, and other text-based information across conversations using semantic vector search.

Integrates with Gmail APIs to manage emails and labels, including sending, deleting, summarizing, and semantic search via RAG.

MCP server providing tools for entity extraction, query refinement, and relevance checking to build Agentic RAG applications.

Enables Codex to run shadow-mode evidence selection by reading source files, scoring passage relevance with Jev or local Eve models, and returning original text with provisional exclusion decisions.

MCP server that ingests PDF documents into pgvector for semantic search and RAG pipelines. It handles extraction, chunking, local embeddings, and storage, enabling agents to make PDFs searchable via natural language.

A semantic search MCP server for YouTube transcripts using OpenAI embeddings and ChromaDB, enabling natural language queries to find conceptually similar content beyond keyword matching.

Exposes publisher journalism to LLMs and agent frameworks via search, retrieval, source grounding, and consistent citation, enabling accurate content retrieval with attribution and policy enforcement.

Generates CanvasXpress data visualization JSON configurations from natural language descriptions using RAG with 132 few-shot examples, achieving 93% exact match accuracy for creating charts and plots.

MCP server for querying survey feedback and statistics regarding the 'Thudong' field exam after the event at Wat Pa Roi Pi Luang Pu Viriyang, Ratchaburi, December 12-15, 2568 (2025). Enables searching impressions, suggestions, and satisfaction statistics across participant groups.

Processes emails from Outlook with date filtering, storing them in SQLite databases while generating vector embeddings for semantic search capabilities in MongoDB.

Enables Claude Desktop to search private documents using Azure AI Search and perform web searches with Bing, providing AI-enhanced results with source citations through Azure AI Agent Service or direct Azure AI Search integration.