DevProjex

DevProjex: MCP / GUI / CLI / TUI all in one

🏆 Selected by the Avalonia UI team for the [App Showcase](https://avaloniaui.net/showcase)

Clean, token-efficient codebase context for AI chats and coding agents. You see exactly what leaves your project, and secrets are masked before it goes.

DevProjex turns any folder or Git repository into clean context for AI. Paste it into ChatGPT or Claude, or let Claude Code, Codex, and Cursor read the project through its read-only MCP server. A desktop app, a Terminal Workspace, a CLI, and the MCP server share one engine, one set of filters, and one masking pipeline, on Windows, macOS, and Linux.

Tick what you need in a file tree, check the live preview and its token estimate, then copy or export the result as ASCII, Markdown, JSON, or XML, or as a clean copy of the project in a folder or ZIP.

🔒 Read-only and telemetry-free by design. DevProjex does not upload your project contents or collect telemetry.

App demo 🖼️

Download 🚀

Microsoft Store: 👉 DevProjex

Latest GitHub release (Windows, macOS, Linux): 👉 github.com/Avazbek22/DevProjex/releases/latest

WinGet (Windows): winget install OlimoffDev.DevProjex

Run without installing

The CLI, the Terminal Workspace, and the MCP server run straight from npm or NuGet, or from a direct release binary:

npx devprojex tree .    # Node.js 20+

dnx devprojex tree . # .NET SDK 10 ./DevProjex tree . # release binary (DevProjex.exe on Windows)

The npm and NuGet packages contain the CLI, the Terminal Workspace, and the MCP server, but not the desktop app. Requirements per platform, the direct headless archives, and the non-root Docker image are all covered in Docs/Installation.md.

Why DevProjex? 💡

Copying files into a chat window one by one doesn't scale. Packing tools are fast, but you see the result after it's packed, not while you choose. And a coding agent with plain file access reads `.env` as easily as `Program.cs`, unless every tool it uses is told to ignore it.

DevProjex works differently: visual, precise, and local-first.

• You see what leaves your project: file tree, live preview, token estimate, and an agent journal that keeps a receipt of every MCP session.
• You control what leaves it: Smart Ignore, Git modes, secret and private-data masking, name filters, saved profiles.
• Your agent gets the same rules: the MCP server is read-only, secret masking there has no off switch, and with Live Context the files you tick are the agent's focus.
• You get more than text: a real project copy as a folder or ZIP.

The numbers, with their caveats. In the final blind series against Repomix (11 tasks, 8 repositories, 6 languages, 22 sessions per side, Claude Haiku 4.5 as the agent and as the judge), DevProjex used 973,020 tokens against 1,174,907, and the judge trusted the DevProjex answer in 17 pairs of 22 against 3. With seven planted credentials, neither tool leaked a value, but the code around them stayed readable through DevProjex in 7 files of 7 against 1 of 7. The tasks were written by the author, Repomix needs fewer tool calls, and it wins broad "how does X work" questions. The whole series, with the agents' and the judge's verdicts verbatim, is in Docs/Benchmark-History.md.

Use it for

• AI assistants: clean input for ChatGPT, Claude, DeepSeek, Qwen, Kimi.
• AI agents: any MCP client reads your project through a server that only reads and always masks, and you steer its focus with checkboxes.
• CI pipelines: fail a build when secrets would leak into packed context, without ever printing the values.
• Restricted environments: get the same clean context where AI agents, remote indexing, or IDE plugins are not allowed.
• Large codebases: pull out one module instead of the whole repository.
• Code reviews and teaching: share the structure and only the files that matter.

Get started

1. Open or drop a project folder.
2. Choose folders, files, filters, ignore rules, and output mode.
3. Preview, then copy, export, run the same workflow from the terminal, or connect your coding agent through MCP → Live context.

Works with any language, repository, or project structure.

Feature overview ✨

Choose and control

• [Smart Ignore](#how-smart-ignore-works-): hides build output, dependency folders, and caches, only when it finds evidence.
• [Hide Secrets](#how-hide-secrets-and-hide-private-data-work-): masks detected credentials in place, in every export and every MCP response.
• [Hide private data](#how-hide-secrets-and-hide-private-data-work-): optionally masks emails, IPs, MACs, phones, and user paths.
• [Code compression](#how-code-compression-works-): keeps signatures, empties function bodies; pure code gets about 3× smaller.
• [Strip comments and blank lines](#how-code-compression-works-): syntax-aware cleanup in 20 language packs; source files untouched.
• File tree with checkboxes, search, and name filters.
• [Git modes](#how-smart-ignore-works-): .gitignore, tracked files, staged files, all current changes, or a ref-to-ref diff.

AI agents

• [Read-only MCP server](#mcp-server-): eight tools for any MCP client, on the same engine as the desktop app.
• [Live Context](#live-context-your-checkboxes-become-the-agents-focus): tick files in the desktop app and the agent works with that selection on its very next call.
• [Agent journal](#agent-journal-a-receipt-for-every-session): a receipt for every session with calls, delivered paths, tokens, and masked values, never file bodies.
• [Hard boundaries](#security-boundaries): root jail, untrusted-data markers, and an agent that can only narrow what it sees.

Preview and export

• Live preview (tree, content, or both) with live counters for lines, characters, and a token estimate.
• Scrollbar markers show search matches and masking findings at a glance.
• Export as ASCII, Markdown, JSON, or XML, to a file or the clipboard, tree only, content only, or both.
• Export a clean copy of your project to a folder or ZIP archive.

Workflow and interface

• Desktop app, Terminal Workspace, CLI, and MCP server: the same engine, four ways to work.
• Git tools built in: clone by URL, switch branches, update cached copies.
• Local profiles remember your settings per project.
• Light, dark, and system themes; platform-native keyboard shortcuts; localization in 20 languages.
• Stays smooth even on very large folders.

Project copy export

Use File → Export project → To folder… or To ZIP archive… to create a separate copy of your current selection. The same workflow is available through devprojex export project.

Project copies respect your chosen root folders, file types, ignore rules, and checked items; if nothing is checked, the whole current tree is exported. Directory structure, binary files, and included empty folders are preserved. When Hide Secrets or Hide private data is enabled, detected values in text files are replaced, binary files remain unchanged, and the result is intentionally not a byte-for-byte copy, so it may not build or run. The source project is never modified, and the result can't be written inside it.

MCP server 🤖

DevProjex ships a built-in secure [Model Context Protocol](https://modelcontextprotocol.io) server, on the official C# MCP SDK, that turns any local folder or Git repository into token-efficient codebase context for AI agents: Claude Code, Codex, Claude Desktop, Cursor, Google Antigravity, VS Code, or any MCP client. It runs on the same engine as the desktop app, the Terminal Workspace, and the CLI. One line connects Claude Code, with or without the desktop app installed:

claude mcp add devprojex -- npx -y devprojex mcp --root /absolute/path/to/project

Under the hood every client starts the same command, devprojex mcp --root /path/to/project, and talks to it over stdio.

Connect a client

• Desktop app: MCP → Live context or MCP → Standard, then Open in Claude Code, Codex, Cursor, or VS Code. The submenu you pick decides whether the registration follows the checked tree.
• Terminal Workspace: mcp connect [live|standard] registers the server without opening another terminal; live mode is the default here.
• CLI: devprojex mcp connect . --client (standard mode unless --mode live is given). Add --open to launch the client, or --print when only a manual configuration fragment is needed.
• Without the desktop app: the npm or NuGet package runs the same server through npx -y devprojex or dnx devprojex. Snippets for every client are in Docs/McpServer.md.

Cursor and VS Code get a project-local .cursor/mcp.json or .vscode/mcp.json; other servers in those files are left alone. For a first-call check, inspect DevProjex with /mcp in Claude Code or run codex mcp list, then ask: “Through DevProjex, show the tree of the current selection.” That call appears in the agent journal.

Live Context: your checkboxes become the agent's focus

Open the project in the desktop app and connect through MCP → Live context. From then on the tree you tick is what the agent works with:

• Tick, untick, done. The agent sees the new selection on its very next call, through the shared local project profile. No restart, no new prompt.
• Focus, not a cage. Tree, search, analysis, dependency, and pack operations stay inside the checked selection. A file outside the ticks can still be read by name, with an outside-focus notice.
• Your filters stay the limit. The desktop app's filters and secret masking apply to everything the agent reads; files your filters exclude stay out of reach.
• Saved results stay honest. A stored pack is pinned to the selection that created it; change the ticks and the agent rebuilds it explicitly.
• See what the agent took. Every file the agent received is marked in the tree with a count, the window title names the active client or session count, and focused paths are restored when you reopen the project.

Live context uses --live; Standard connects the same server but does not follow the window selection.

Eight read-only tools

Eight read-only