"All items" matching MCP servers:

Integrates CopyQ clipboard manager with LLM agents, enabling reading, writing, searching, and managing clipboard items organized in tabs with tags and notes through a unified interface.

Enables AI assistants to scan a Mac for reclaimable disk space and safely move selected items to the Trash, with dry-run defaults, protected paths, and confirmation before permanent deletion.

Enables AI clients to search and count indexed files and folders through Everything's HTTP JSON API, retrieve real-time file metadata, reveal items in Explorer, and automatically launch Everything with UAC when needed.

Enables parsing German bank statement PDFs into structured, validated transaction data, exporting all transactions as German-style CSV, and verifying statement totals via proof calculations, all locally within MCP-compatible clients.

Parses PDF receipts to extract grocery and shopping expenses, automatically categorizes items using smart rules and LLM fallback, and stores them in a local SQLite database for querying purchase history and spending patterns.

Enables MCP clients to browse, search, read, write, upload, download, create folders, and delete items on a Filen cloud drive through stdio-based tools.

Enables Claude AI to open files and directories with system default applications or specified apps, and reveal items in macOS Finder.

Manages backlog items and todos with status tracking, priorities, and dependencies. Stores work items as human-readable markdown files with automatic versioning.

A local PDF manipulation server for AI agents that provides tools for merging, splitting, extracting info, and converting images to PDF, all without uploading files.

Enables cataloging and managing personal inventory (items, attachments) through natural language, allowing users to add, search, update, and retrieve item details and attachments via MCP tools.

Enables AI assistants to append completed work items to the checklist of the newest daily log file in a configured directory, keeping notes updated without exposing file paths.

Enables an AI assistant to measure macOS disk usage, investigate unfamiliar files and folders, identify cleanup candidates, and prepare numbered cleanup proposals that move approved items to the Trash only after server-side path checks.

Enables agents to run millisecond-level filename searches against the local Windows file index using full query syntax for names, paths, sizes, dates, wildcards, regex, and duplicate or empty filters. It also supports hit counting without transferring result rows, index and status checks, recently modified items, and duplicate-name detection, all without directory traversal or cloud services.

Enables MCP-capable agents to locate game save files, identify their engines, compute unlock plans for gallery/recollection flags, diff saves, and safely dry-run, apply, verify, or roll back reversible byte patches with automatic backups.

A proof-of-concept MCP server for AI assistant note-taking, enabling adding notes, fetching the latest note, and summarizing all notes.

Provides a stateless Streamable HTTP MCP endpoint with 16 tools for browsing, searching, reading, writing, organizing, importing, and linking files across a read-only drive and writable workspace, including moving items between views and publishing or syncing changes back.

Enables natural language todo list management through Claude Desktop with YAML-based persistence. Supports creating, completing, deleting, and listing todo items with automatic timestamp tracking and secure file permissions.

MCP server for translating PDFs using pdf2zh-next, preserving document context by extracting all text segments for LLM translation at once.

Reads and searches local email archives (.mbox or .eml) with full MIME parsing, enabling queries about senders, subjects, dates, and bodies while keeping all data on your machine.

Enables Claude to create, edit, run, and manage reusable skills stored locally, including executing scripts with automatic dependency management and environment variables. Works across all MCP-compatible clients like Cursor, Claude Desktop, and claude.ai.

A server that allows LLMs to run Claude Code with all permissions bypassed automatically, enabling code execution and file editing without permission interruptions.

Provides 13 ZIP tools for AI agents: inspect and list entries without extracting, verify integrity, extract with zip-slip, zip-bomb, and symlink guards, create deterministic reproducible archives, and modify ZIPs without recompression, all with no network access.

Enables an AI assistant to reliably read and chunk PDF/text documents, validate extracted JSON against a schema with full error paths, and save structured output—all confined to a single allowed directory.

An MCP server that gives Claude direct access to your reMarkable tablet's notebooks, enabling document search, PDF rendering, handwriting transcription, and diagram conversion, all locally without API keys.

Enables AI agents to convert Markdown documents and multi-file books into PDFs, recover Markdown from PDFs that embed their source, and open notes in a live preview GUI, all without a browser, LaTeX, or Pandoc. Each conversion returns the PDF plus page count and rendering diagnostics, and produces byte-identical output on every run.

Enables AI apps to edit PDFs on the local machine through natural language, merging, splitting, extracting, rotating, deleting, reordering and duplicating pages, plus inspecting page counts and encryption status. All work runs locally with no uploads, and every operation writes a new file beside the untouched original.

Enables coding agents to browse, read, search, and write files inside a locked workspace, run asynchronous shell commands, and batch read operations, all with validated caching, health diagnostics, and a SQLite audit trail.

Converts Office documents, images, and e-books to PDF and transforms PDFs by merging, splitting, rotating, numbering, watermarking, compressing, protecting, or unlocking them, plus PDF-to-Word and PDF-to-image conversion, all driven by natural language. Files stay on the user's computer apart from the conversion itself, which runs on EU-hosted servers in France.

Lets AI assistants read a student's Canvas LMS courses, modules, deadlines, announcements and course files through the Canvas REST API, using university single sign-on with MFA instead of an API token, and download lecture slides into per-course folders. All access is read-only and works with any Canvas site, defaulting to Oxford.

macctl is an accessibility-first macOS desktop automation MCP server that lets AI clients see the screen, inspect app accessibility trees, control mouse/keyboard, manage windows, and run commands, all behind tiered permissions and audit logging.