"Y Combinator" matching MCP servers:

Outbound-only remote shell, detached long-running jobs, and temporary file courier for AI agents. Hosted Streamable HTTP plus stdio via npx -y @aicommander/mcp.

Enables AI agents on Windows to read, write, copy, move, and delete files inside WSL distributions, run shell commands in a login shell, and convert between Windows and Linux path styles. Commands are piped to bash -s via stdin so quotes, $, backticks, and other special characters pass through without Windows shell escaping errors.

A high-performance Model Context Protocol server that enables AI agents to extract text, images, and metadata from PDF documents using parallel processing. It features intelligent Y-coordinate content ordering to preserve natural reading flow and supports both local files and URL-based sources.

A tuned filesystem MCP server for Codex-style development, offering fast file operations, bounded output, and safe edits.

Enables managing Baidu Netdisk files through the bdpan CLI and optional Baidu Netdisk Open Platform OAuth tokens, covering capacity checks, directory listing, search, upload, download, copy, move, rename, and delete within authorized folders. Supports multiple accounts with per-account isolation and download verification by size and SHA-256.

A self-hosted MCP server that enables AI coding agents to read, edit, search, and run code in local projects with human review loops and policy controls.

Enables ChatGPT, Claude, and other web MCP clients to access and operate multiple VS Code workspaces through tools such as read, bash, edit, write, and workspace_info, with per-workspace tokens and role-based permissions.

Provides a secure MCP tool to append confirmed parking reservations to durable storage with validation, audit logging, and concurrency safety.

Enables searching, reading, and summarizing local files and Google Drive content through natural language.

Enables users to index local Markdown articles and then search, filter, list, and retrieve them through MCP tools while keeping all content on the local machine.

Enables Claude Desktop to add, retrieve, update, delete, and list personal notes persisted in a local JSON file, with atomic saves and configurable note storage paths.

Enables validation and retrieval of metadata from Markdown files in the Subordinación y Valor project. Validates metadata against project specifications and extracts structured metadata from Markdown documents.

Stores and retrieves personal information fields securely, allowing Claude to access your name, address, email, and professional details without re-typing them.

Works out a health plan from your own record: which screening is due and evidence-based suggestions with citations. Reads and writes one health-roadmap.json file on your machine; nothing is sent to a server.

Enables secure filesystem operations with directory sandboxing and optional read-only mode. Supports file reading/writing, directory management, file searching, and text operations while restricting access to specified directories.

Enables AI assistants to read local documents by converting PDFs, Office files, images, and audio to Markdown on-device, without uploading them.

Provides bounded, read-only analysis of local project directories, enabling inventory, marker detection, and safe file reads without executing code.

Read selected local folders from ChatGPT on macOS, with per-folder read-only or read-write access and hash-checked, recoverable edits. Requires local installation and a private ChatGPT app. The Glama container is a synthetic evaluation demo; it does not connect to files on your Mac.

Enables AI assistants to read, edit, and execute Jupyter notebook files (.ipynb) with live kernel output, without requiring JupyterLab.

Enables natural-language diagnosis of Linux system issues by providing sandboxed, typed tools for system, service, filesystem, and git inspection, with human approval for mutating actions.

Analyzes unstructured documents in a local folder, extracting structure and key terms, and supports generating summaries via a host LLM with validated, approval-based report saving.

Mac file and terminal tools for local AI clients, plus an opt-in ChatGPT Developer Mode relay. Checked edits, bounded reads and real exit codes. Free MIT agent; OpenAI listing under review. Owner-level access, not a sandbox.

Enables agents to run read-only coverage and staleness checks on local folders and documents, reporting missing periods or mismatched figures without writes, deletes, or network calls.

Enables an AI assistant to prepare and run Divinity: Original Sin 2 Game Master mode campaigns by reading and editing campaign files with backups and by controlling the running game through a Script Extender bridge.

Provides direct, unsandboxed local machine access via filesystem, Python, Node.js, and shell commands for MCP agents.

An MCP server for reading, rendering, and searching PDF files, specifically optimized for LLMs to extract text, tables, and technical diagrams. It enables metadata retrieval, multi-format text extraction, and page-to-image rendering using PyMuPDF.

locidx

Enables MCP clients to read local academic PDFs, render pages, extract reference lists, and search papers by keyword with deterministic page-level access.

Private, EU-hosted file transfer for AI assistants. Ask what arrived and who downloaded it, share files as expiring links, and email them to people, with every send confirmed by you. Hosted at https://yungle.co/mcp with one sign-in (OAuth, no key), or run locally with npx -y yungle-mcp. Never deletes, revokes or invites.

Enables AI assistants to browse, read, write, move, copy, and delete files on WD MyCloud Home devices, supporting local SMB and remote REST API connections with automatic token refresh.

A universal resource server that enables AI models to mount local folders, scrape web pages into Markdown, and query SQLite databases without writing code. It features a real-time TUI dashboard and persistent configuration for managing diverse knowledge sources.

Provides secure filesystem access for AI models through the Model Context Protocol with strict path validation, file operations, directory management, and system command execution within predefined directories.

Enables reading, writing, editing, searching, running commands, transferring files, and using git on a remote Linux server over SSH via MCP tools.

Enables two or more Claude Code terminals on the same machine to communicate by registering and sending messages via the local filesystem.

A Model Context Protocol (MCP) server that enables AI assistants to perform comprehensive file operations including finding, reading, writing, editing, searching, moving, and copying files with security validations.

A comprehensive tool server for reading, merging, and extracting content from PDF files via local paths or direct URLs. It enables metadata retrieval, regex searching, and page-specific text extraction with built-in caching and workspace-restricted security.

Enables AI agents such as Cursor and Claude Code to inspect local log files through MCP tools for tailing, searching, filtering, statistics, and root-cause diagnosis using local Ollama or a built-in rule engine.

Enables AI clients to manage and manipulate text files in a secured local directory through tools like list, read, write, delete, create directory, and move.

A TypeScript-based MCP server that enables Claude Desktop to perform file operations and retrieve system information, with built-in security features that restrict access to safe directories only.

Enables agents to compress JPEG, PNG, and WebP images to a target byte size, split PDFs by page or ranges, and remove image metadata while processing local files without sending file bytes over the network.