"Instructions for accessing Gmail messages programmatically using a cursor" matching MCP servers:

A FastMCP server for Cursor platform APIs enabling spend guardrails, cloud agent monitoring, and inter-agent inbox messaging.

Enables remote control of the Cursor AI agent via chat platforms like GitHub Issues or Telegram, allowing users to start sessions and receive summaries and prompts in a chat thread.

Scoped, low-latency persistent memory layer for AI agents, Cursor, and Claude Code over Model Context Protocol with sub-50ms hybrid search.

Enables MCP clients like Claude Code and Codex to delegate coding tasks to Cursor's CLI agent, which implements changes in the workspace and returns clean, structured results for review.

Monitors your Cursor usage and provides a conserve flag to the agent, helping you manage request quota by batching questions, preferring defaults, and cutting unnecessary confirmations.

It enables AI assistants to search, read, and draft email in a Gmail inbox, and at the highest access level to send mail and reorganize labels, archive, or trash messages. Access is gated behind three levels — read-only by default, drafts-only, and full — so the model is only offered the tools its configured level permits.

gmail-mcp is a remote MCP server that exposes Gmail as a set of tools — search, read, label, draft, send — over streamable HTTP with OAuth 2.1. It runs on Cloudflare Workers under your own domain.

A Python bridge for interacting with the macOS Messages app using MCP (Multiple Context Protocol). Simple install using uvx mac-messages-mcp

Enables AI assistants to search, read, draft, and send Gmail messages, as well as manage labels and trash using natural language.

A local MCP server that provides Gmail tools (search, read, send, draft, label management) while keeping your emails only between your machine and Google, with no third-party access.

Enables cost-effective repository analysis, code search, file editing, and task planning by wrapping the cursor-agent CLI through focused tools. Reduces token usage by offloading heavy thinking tasks from Claude to specialized operations with configurable output formats.

Cross-chain cryptocurrency swaps via Chainflip. Get quotes, execute swaps, and track progress. No API key required to get started.

Provides agents with real Linux VMs to run commands, manage files, expose ports, and track costs, all through an ephemeral sandbox service.

MCP server for Pi Network that enables AI agents to query Pi chain data (balances, transactions) and verify user tokens, with optional payment sending that is off by default.

Discover and connect your agents with other agents via A2A protocol. Share resources for free or fee.

Enables AI agents to execute SSH commands, read files, and list directories on remote hosts with a configurable command-safety policy.

A fault-tolerant, stealth-enabled Model Context Protocol (MCP) server for web searching and content fetching. Built for AI Agents (Cursor, Claude Code, OpenCode), it uses a stealth browser engine to fetch pages, dynamically handles SPAs/React, and converts bloat into token-optimized Markdown.

Hebbian learning MCP server with neural memory graphs, eligibility traces, and three-factor reward signals. Associative memory that strengthens through use.

An MCP server that grants AI agents unrestricted file system, Python, and PowerShell access on Windows for real, unfiltered automation.

Enables Claude to interact with FTP servers through natural language commands, allowing users to list directories, download/upload files, create directories, and delete files/directories on FTP servers.