"All MCP servers available on the site" matching MCP servers:

Enables a machine to expose its registered folders and locally added tools to remote callers over MCP, deciding each request against local policy with default-deny access, per-person tool grants, pre-approval for anything not marked read-only, and an on-machine audit log. Also runs a folder file server offering directory listing, text reading, and text writing where permitted.

Enables editing a static website from any MCP host using a private working copy, live preview, revision history, and checkpoints, while keeping pause, undo, restore, and export under human control until explicitly confirmed.

Enables MCP clients to read bounded workspace files, validate exact replacement plans for the VS Code extension, and check recent typing progress without modifying source or running shell commands.

Connects ChatGPT to local files, terminals, and the desktop through MCP with Chrome integration, letting users read and edit project files, run commands, and follow tool results as they arrive. It also adds durable multi-agent workers, Goal/Loop task tracking, mid-task corrections, and Compact & Resume for carrying session and worker history into a fresh chat.

Enables ChatGPT to access approved local Windows folders, run commands, control the desktop, and manage session history through a permission-bounded MCP server.

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 read-only remote MCP server that searches and reads files from a personal Microsoft OneDrive folder via Cloudflare Workers, enabling live access without a local workstation or tunnel.

Enables ChatGPT's web interface to operate a real Mac by executing shell commands and reading or writing files over a reverse SSH tunnel, without installing a client or consuming API quota.

Gives ChatGPT hands-on control of a local machine: reading, patching and executing code in approved project folders, running real interactive processes, managing plans and worker sub-chats, and driving the browser or desktop through user-granted permissions. Every capability is a switch inside an approved-folder sandbox, so nothing runs that the user did not explicitly enable.

Enables AI assistants to deploy static websites to the Demox platform with automatic directory packaging and cloud storage integration. It includes tools for managing deployments, such as listing, viewing, and deleting websites.

Enables ChatGPT to work on a local project by reading and editing files, running shell commands, keeping terminals and desktop sessions open, and splitting work across durable workers whose context persists between tasks. Long-running work can be steered mid-flight, tracked with Goal, and carried into fresh chats via Compact & Resume.

Lets ChatGPT work directly on a local project by reading and editing files, running shell commands and tests, keeping terminals open, and using the user's desktop, all paired with an approved workspace folder. It also splits independent jobs across persistent workers that retain context, while riding the user's existing ChatGPT plan rather than Codex quota.

Enables comprehensive local file system operations including searching and reading content from various formats like PDF, Office documents, CSV, and text files. It features automatic character encoding detection and secure path validation for directory access.

A local MCP server that gives Claude in the browser tools to interact with a Fedora machine, including file operations, system diagnostics, build tasks, and root actions via Polkit.

A production-grade Model Context Protocol server that enables secure management of context data through a React dashboard, supporting ZIP processing, context approval workflows, and system monitoring.

An MCP server that converts files between formats using locally installed tools, with no data leaving your machine and automatic adaptation to available converters.

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 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.

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.

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.

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.

An MCP server for controlled server operations via BaoTa Panel, providing 50+ tools for system, site, database, files, cron, Docker, and network management with safety features like permission tiers, credential masking, and audit logs.

A local-first PDF tool for merging, splitting, rotating, watermarking, Bates-numbering, cleaning metadata, and counting pages — all operations happen on your machine with no network transmission.

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.

Enables AI coding tools to read, write, search, and list files on remote machines and run commands there, including background long-running jobs and TTY-based interaction, all through a single persistent SSH connection. Bypasses the cost of establishing a new SSH session on every call, cutting typical multi-step remote operations from seconds to milliseconds.

Enables an AI assistant to track credit-report disputes with consumer reporting agencies and furnishers, compute statutory response deadlines, and draft dispute letters into local text files. All records stay in a folder on the user's own computer, with approval required before any dispute is deleted.

Enables agents to read and write CapCut desktop draft folders on local disk, assembling vertical 1080×1920 shorts with clips, titles, subtitles, music, transitions, and effects as drafts the user then opens and exports in CapCut. All writes are dry runs until explicitly disabled, and existing drafts are backed up before overwriting.

Enables Claude Code sessions to read and edit OrcaSlicer presets, clone profiles, inspect saved plates, and search the OrcaSlicer wiki, all without OrcaSlicer running.

MCP server for the Rclone RC API. Gives AI assistants the ability to manage cloud storage remotes, copy/sync files, list directories, and more — all through natural language.

Enables local, private analysis of CSV and TSV files through natural-language agents such as Grok Bot and Cursor, offering file listing, profiling, SQL-like queries, summaries, group-bys, pivot tables, cleaning previews and generated charts. All computation happens on the user's own machine against an allowlisted folder, with no network calls, telemetry or data leaving the host.