"Using Gemini CLI for research purposes" matching MCP servers:

A Windows-compatible Model Context Protocol server that enables AI assistants to interact with Google's Gemini CLI, supporting file analysis, large context windows, and safe code execution.

CLI + SDK + MCP server for ZSpace (极空间) NAS — zero-config file management from the terminal or AI agents. No password, no SSH: reads the desktop client's login state. 12 MCP tools covering ls / find / tree / upload / download / rename / move / copy / remove.

Z-CLI provides NAS operations like file management, pool queries, search, and file operations through CLI and MCP Server, enabling AI assistants to interact with zspace private cloud.

Enables autonomous web research, file management, and dynamic UI dashboard generation through Gemini LLM and FastMCP.

Lets Claude Code drive a Qodalis CLI server, exposing that server's CLI commands, filesystem, data explorer, jobs, and plugin tools with the configured account's permissions. It handles token or password sign-in, automatic reconnection after drops, read-only filtering, and client-side allow/deny lists.

An MCP server exposing calculator, file read, and file write tools for the Gemini CLI agent, enabling mathematical computations and file operations through natural language.

50 tools and 400 functions for working with Excel/.xlsx spreadsheets — read/write, recalculate formulas, diff, repair broken references, and audit. Built for AI agents.

An MCP server that exposes macOS Spotlight search as tools, wrapping mdfind and mdls to provide full-text and metadata file search across the system.

A local AI agent workspace that allows users to interact with simulated data files via custom slash commands and context mentions, powered by Google GenAI SDK and MCP.

A local MCP runtime that lets MCP clients such as ChatGPT inspect workspaces, search, read, write, and patch files, manage directories, run shell commands, and control persistent processes on your machine through an outbound Device Relay connection that needs no open inbound port. It can also publish a local loopback OpenAI-compatible model runtime as a Frely personal Provider.

MCP server for the Obsidian CLI with controlled profiles for governed read-only and mutation operations, plus a personal-unrestricted profile for full access.

Bridges CLI tools to AI assistants via MCP, enabling knowledge graph management and file reading capabilities.

Intelligent file search engine with Frecency ranking, fuzzy matching, and Git awareness. Provides MCP server for AI agents to search files, content, and get file statistics via natural language.

MCP server wrapping the agy CLI, enabling querying, web search, and file writing through tools like ask-agy, search-web, and write-file.

Enables MCP clients to interact with an Obsidian vault through the official Obsidian CLI, supporting search, notes, tasks, files, links, and native Canvas operations while the Obsidian desktop app is running.

Enables AI agents to create, read, view, and edit Apple Numbers spreadsheets through the Model Context Protocol, leveraging both a parser engine and the Numbers application for formula evaluation and export.

A collection of small MCP servers for macOS automation that expose Apple Mail, MoneyMoney, and Spotlight functionality as tools via AppleScript and command-line, enabling AI applications to search mail, manage contacts and transactions, and perform system-wide file searches through natural language.

Local-first, file-based memory layer for AI agents — one shared Markdown vault across Claude, Codex, Gemini, Cursor and any MCP client. Provides read/write memory tools with an audit trail, per-agent trust levels, and Git sync; no cloud and no lock-in.

Gives Claude and other MCP clients full control of a running Obsidian vault through the official Obsidian CLI, with fast filesystem reads for bulk operations and link-safe writes via the app.

Enables AI agents to perform local video, audio, and file operations inside an isolated workspace, including cutting/concat videos, extracting audio, transcribing, and managing files, with typed responses and background job support.