"How to send an email" matching MCP servers:

Enables users to connect to their email inbox via IMAP to search, filter, and summarize emails based on criteria like subject, date, and sender. Supports marking emails as read and provides customizable email summarization with various prompt options.

Analyzes meeting transcripts to determine if they could have been emails, returning filler word count, decisions, action items, and a suggested email.

Enables natural language management of Gmail through MCP tools for searching, analyzing, summarizing, drafting, and sending emails, with AI reasoning and user confirmation for actions.

Enables intelligent Gmail management, including email triage, newsletter classification, promotional email cleanup, summarization, filter suggestions, draft replies, and audit logging.

Enables AI models to fetch and summarize Gmail messages, send emails with attachments, and convert text content into PDFs. It streamlines email-based workflows like automated reporting and task management through the Model Context Protocol.

Enables local analysis of unstructured documents (PDF, DOCX, PPTX, SVG, PNG) by extracting text and structure with citation anchors, and verifies summaries against source material before a human approves saving a report.

Model Context Protocol server for Archive of Our Own: search fanfiction and have an AI read and rank fics for you.

tooltrim reduces the tokens agents spend re-reading bloated tool results. Run it as an MCP server exposing compress and expand_tool_output, or as a gateway in front of any upstream MCP server: it re-exposes the upstream tools unchanged and shrinks each result (HTML/JSON/logs/tables) before it reaches the model, keeping the relevant content only.

Two self-hosted MCP servers: manage a local model machine (Ollama pull/switch, LoRA training) and bridge to local Ollama/vLLM for pure language processing tasks (writing, summarizing, classifying, extraction) without giving the calling agent tools or file access.

Allows AI agents to fetch, search, and summarize YouTube video transcripts without an API key, including chapter summaries.

A FastMCP server that enables AI assistants to extract structured information from unstructured text using Google's langextract library through a secure, optimized Model Context Protocol interface.

An MCP (Model Context Protocol) server specialized in deciphering PDF internal structures.

Enables LLMs to interact with Fathom.video API for managing meeting recordings, retrieving transcripts and AI-generated summaries, searching meeting content, and accessing analytics and team data.

Exposes the Aporix document optimization API as an MCP tool for AI agents, enabling document compression and token/cost savings analysis.

Keyword Extractor AI - MCP server providing AI-powered tools and automation by MEOK AI Labs

23 developer & data API tools for AI agents - IP/DNS/WHOIS/SSL lookups, web scraping & screenshots, text AI (summarize, translate, sentiment, grammar, redact), and dev utilities (hash, UUID, QR, JWT, cron, IBAN/VAT/email validation, breach check).

Turns plain text or Markdown, web pages, and local PDFs into editable Markdown outlines that can be rendered as standalone, offline-capable interactive HTML mind maps. Works with any MCP client with no API key required, since the connected model writes the final outline from a draft and cleaned source text.

Unofficial MCP server for working with Kagi without API access (you'll need to be a customer, tho). Searches and summarizes. Uses Kagi session token for easy authentication.

Enables AI agents to transcribe, translate, and summarize audio via Zoom AI Services APIs, providing an 'ear' through tools like transcribe_audio, summarize_transcript, and translate_text.

MCP Long Context Reader is a Python-based toolkit designed to overcome the context window limitations and high costs associated with Large Language Models (LLMs) processing extensive documents. It provides a FastMCP server with multiple, powerful strategies for an LLM agent to 'read' and query long documents without needing to load the entire text into its context window.