"Finding tasks for large language model agents" matching MCP servers:

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.

Enables downloading real binary files from Egnyte and uploading large files with chunked support, complementing the official Egnyte MCP connector.

Enables intelligent handling of large files through smart chunking, search with regex support, line navigation, and streaming capabilities without loading entire files into memory.

A comprehensive and efficient Model Context Protocol server for task management that works with Claude, Cursor, and other MCP clients, providing powerful search, filtering, and organization capabilities across multiple file formats.

Enables an AI agent to host a shared folder or join an invite link as a participant in a collaborative editing session, reading, editing, and writing the files the room shares. Runs the same sync engine and wire protocol as editor clients, so an agent and a person or another agent converge on the same documents and see each other's changes.

Provides FastMCP-based servers with various tools for AI assistants including math operations, file management, note-taking, todo management, and database operations. Offers both basic and advanced server configurations with tools, resources, and prompt templates.

Enables AI assistants to extract and query Obsidian Tasks from markdown files, supporting task metadata and advanced filtering via Obsidian Tasks query syntax.

Converts Cursor agent plans into structured markdown task lists and organizes them in your repository.

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 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.

Secure localhost MCP gateway that exposes project-scoped file/Git/search tools and controlled CLI agent adapters (Codex, Claude) with fixed argv for safe Windows-native agent work.

MCP server that encapsulates Apple Mail on macOS via AppleScript, enabling invoice PDF search, attachment saving, and message flagging through natural language.

A native Nextcloud app that exposes the instance as an MCP server so Claude and other MCP clients can read, search, and (with admin-granted permissions) edit files, notes, calendars, Deck cards, and Talk conversations. It runs inside Nextcloud with OAuth or app-password sign-in, applying each user's own Nextcloud permissions and admin-controlled per-operation grants.

Serves read-only tools that let an agent inspect PDFs step by step: outline a document, search for text or figure values, read pages and tables in order, describe figures and chart data, and render page or block images, with every block cited to its page and bounding box. It also lists the PDFs available under a configured root folder, which it never reads outside of.

Self-hosted MCP coding server and unified local Control Center for ChatGPT web, enabling file editing, command execution, Git operations, and optional upstream MCP tools with conversation access controls.

Fast PDF tools for AI agents: 31 tools in one Rust binary. CLI, MCP server and library.

MCP server for Obsidian vaults, optimised for Cursor agents — safe note editing, lean tool surface, direct filesystem access.

A simple MCP server for managing tasks via a local JSON file, demonstrating resources, tools, and prompts for task reading, creation, and analysis.

TheWeave is a markdown-native memory architecture for Claude and any MCP-aware agent. Your agent's memory lives as plain .md files you own: a 5-verb MCP core over the vault, query-driven PageRank retrieval, bi-temporal facts (valid_from / valid_until), and a persona-as-vault model. No database and no embeddings server. The files are the memory, inspectable in your editor and versionable in git.