"A web browsing and summarization service" matching MCP servers:

Enables ChatGPT web to use local tools like file reading, command execution, and patch application through an MCP server over OpenAI Secure MCP Tunnel.

Local MCP server bridging ChatGPT Web to local tools for file, shell, git, test, and process management with secure policy controls.

Enables a browser-based AI assistant to read code, edit files, run tests, inspect failures, and keep task checkpoints on a local project.

Enables local code execution via Codex (Luna) through MCP, using ChatGPT Web conversations as a planner. Provides file, terminal, and code execution tools while keeping long-running jobs manageable.

Pluggable local agent capability hub that gives web-based DeepSeek local Agent capabilities (MCP/file operations/skills/desktop automation) and lets local agents reuse the same tools.

Enables clipping web pages to Markdown with local images, supporting CSS selectors and content analysis.

Enables ChatGPT to save conversation attachments, generated files, and images directly into a configured local macOS project directory with OAuth-secured MCP access.

MCP server for agentic-first PDF review of LaTeX papers, enabling commenting, compiling, and visual inspection via Claude Code.

Exposes an authenticated local runtime over OpenAI Tunnel so ChatGPT can inspect authorized Windows workspaces, read bounded Git status and diffs, submit and cancel Codex CLI tasks, and use workspace Skills. It also brokers connections to optional loopback stdio or HTTP MCP services, such as Stata and Zotero, with explicit tool allowlists and loopback-only access.

Enables document conversion between PDF, DOCX, and Markdown formats to facilitate reading and editing complex files in AI tools like Claude Desktop or Cursor. It utilizes marker-pdf and pandoc to provide structured text versions of documents, helping to manage context and support unsupported file types.

A self-hosted OAuth MCP server that connects ChatGPT developer mode to an isolated coding workspace for listing and opening projects, reading and editing files, running shell commands, and observing or acting on terminal sessions.

An MCP server that gives LLM clients access to a SQL Server database and the local filesystem, including file operations and image handling.

Enables a local AI assistant to search the web via DuckDuckGo, fetch and extract readable text from web pages, and save research notes as Markdown files to a chosen directory.

locidx

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 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.

A Model Context Protocol (MCP) server for ZeroDrive file management. It enables AI assistants like Claude to interact with ZeroDrive cloud storage through a standardized interface.

Enables AI clients to securely execute remote commands and transfer files over SSH through standardized MCP tools, with multi-host management, flexible authentication, and an admin console.

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.

Enables cloud AI agents to safely work on a Mac through MCP-style JSON-RPC by providing approval-gated command execution, jailed file access, signed requests, and a tamper-evident audit log. Risky actions require on-device approval, while files remain confined to a chosen folder with recoverable writes and deletions.