
ReMCP
io.github.antonbaiderPublished by GitHub account antonbaiderv0.2.79Updated Sep 28, 2026
Securely use files, terminals, screenshots and processes on computers you pair with ReMCP.
Overview
ReMCP connects a computer you pair to an AI client, letting the assistant read and write files, run terminals, take screenshots and control the desktop.
- What you can do
- Read and inspect files, images, binaries, directories, hashes and diffs
- Write, patch, replace, move, copy, archive, trash or delete files and folders
- Start and manage processes and terminals, read their output and terminate them
- Take screenshots, record the screen, and drive native windows, keyboard, pointer and clipboard
- Control Chromium browser tabs through CDP and run diagnostics such as services, event logs, network and installed apps
- Read and edit DOCX, XLSX and PDF documents
- When to use it
- Useful when you want an AI client such as ChatGPT, Codex, Cursor, Claude Code or Gemini CLI to work directly on a machine you own or administer, for coding, file management, desktop automation or diagnostics, instead of copying files in and out by hand.
- Requirements
- A remote MCP endpoint plus a device agent installed on the target computer through a one-command installer or npx; the installer may fetch a checksum-verified Node.js runtime into the user profile. A ReMCP account with OAuth sign-in and a single-use pairing code generated in the authenticated workspace. No sudo required.
Installation
In SourceWeft
- Open ReMCP in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.antonbaider%2Fremcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"remcp": {
"type": "http",
"url": "https://remcp.site/mcp"
}
}
}README
Your computer. Your tools. One secure MCP connection.
[npm] [runtime] [npm downloads in 30 days] [npm downloads all time] [Node.js] [license] [GitHub stars]
[ChatGPT plugin] [Codex plugin] [Claude Code plugin] [Cursor MCP] [Gemini CLI extension] [MCP clients] [Kiro Power] [Cline MCP Marketplace] [Smithery directory] [Glama quality score] [Awesome Remote MCP Servers] [Official MCP Registry]
Website · Plugins · Docs · Tool reference · Security · Privacy · Support
ReMCP connects a computer you own or administer to ChatGPT & Codex, Cursor, Claude Code, Gemini CLI, Kiro, Cline, or another MCP client. The device agent makes an outbound connection only — no inbound port, no tunnel, no third-party desktop relay. This repository contains the public device client/runtime, portable Agent Plugin metadata, the Gemini CLI extension manifest, official MCP Registry metadata, and the host-specific OpenAI and Anthropic plugin packaging.
Packages
Install
Open ReMCP → Connect a machine. The page detects the computer's operating system and shows the correct one-command flow.
Windows PowerShell — no preinstalled Node.js, npm, npx, or winget required:
ReMCP keeps its Windows runtime privately under %LOCALAPPDATA%\ReMCP; it does not install Node.js
globally or add the private runtime directory to the system PATH.
macOS / Linux — no Node.js or npm needed beforehand:
The installer asks before installing a vetted, checksum-verified Node.js runtime into your user
profile when needed. It then runs the production-compatible ReMCP version. No sudo required.
The downloaded script is parsed in full before any installation actions begin.
If Node.js is already installed, the advanced npm shortcut is npx --yes @remcp/remcp@latest connect.
For inspecting the script before running it, open https://remcp.site/i.sh in your browser.
The browser can also generate a one-time pairing command. Run that exact command on the computer you want to connect; it installs the runtime and registers the background service.
Pairing codes are generated in the authenticated workspace, expire automatically, and are single-use. Do not invent or reuse a code from documentation.
Commands
Plugins
For users, ReMCP is catalog-first:
Install from your AI host → sign in to ReMCP → use your paired computers.
You do not need to paste an MCP server URL, edit a manifest, clone this repository, or configure a local path just to use the published plugin.
Shareable install guides:
- ChatGPT & Codex: https://remcp.site/install/chatgpt
- Claude Code: https://remcp.site/install/claude
ChatGPT & Codex / OpenAI
ChatGPT and Codex share OpenAI's public plugin directory.
- Open https://chatgpt.com/plugins.
- Search for ReMCP and open the ReMCP plugin card when it is available.
- Choose Install plugin.
- If prompted, choose Connect and complete ReMCP OAuth.
- In ChatGPT, use @ReMCP when you want to invoke it explicitly. In Codex, use Sources → Use plugins → ReMCP.
If ReMCP is not visible yet, the listing or rollout is not available to that account. There is no manual MCP endpoint an ordinary plugin user needs to configure while waiting.
Claude Code / Anthropic
ReMCP was submitted through Claude Platform on September 18, 2026 and currently shows Submitted and pending review.
After approval:
- Open https://claude.com/plugins. In Claude or Claude Desktop, you can also use Customize → Plugins → + → Browse plugins.
- Search for ReMCP and confirm it supports Claude Code.
- Choose Install.
- Complete ReMCP authorization if Claude asks you to connect.
- Ask Claude Code to use ReMCP on a computer already paired to your account.
While the listing is under review, ordinary users do not need to add a marketplace, clone this repository, or paste an MCP endpoint. Developer and reviewer workflows live in the technical guide.
Start with Plugin overview →.
Cursor and the wider MCP ecosystem
ReMCP publishes host-native metadata for coding agents plus directory records for MCP discovery:
The same ReMCP OAuth account and paired computers sit behind every route. Marketplace and directory surfaces change discovery; they do not create separate ReMCP backends.
Distribution manifests, direct install commands, and review links are documented in PLUGINS.md → and DISTRIBUTION.md →.
Developer / reviewer internals
Host-specific manifests, MCP configuration, validation commands, submission artifacts, and local development workflows remain documented separately:
The OpenAI files and Claude files deliberately do not overwrite each other. Release checks fail if either host-specific contract drifts from the shared ReMCP version or production endpoint.
Use ReMCP with Docsy
For source-linked developer documentation alongside local computer access, combine ReMCP with the separate Docsy AI / MCP Plugin. Docsy exposes five read-only public documentation tools (resolve-library-id, list-library-versions, query-docs, search, fetch) through https://docsy.remcp.site/mcp/registry and requires its own OAuth 2.1 authorization. ReMCP's device tools and Docsy's documentation tools remain separate services.
The local runtime
@remcp/runtime is a clean-room MCP server written for ReMCP. It is not a fork of, and shares no code
with, DesktopCommanderMCP or any other MCP
server.
84 granular device operations, 10 hosted production definitions. Current production advertises 8 device-facing façade tools plus 2 account/fleet tools, all model-visible. If custom widgets are explicitly re-enabled, discovery expands to 15 definitions by adding 5 app-only UI helpers. See the generated full tool reference for every current façade and its operation list.
Device runtime surface:
The hosted ReMCP endpoint currently advertises 10 model-visible tools with REMCP_CUSTOM_WIDGETS_ENABLED=false; no app-only render/save/refresh helpers or structuredContent.preview references are exposed. The compact surface routes to all 84 granular runtime operations, and 101 compatibility names remain callable for cached clients without inflating discovery for new models. If widgets are explicitly re-enabled later, the hosted catalog expands to 15 definitions and 106 compatibility names. Each online device returned by list_devices reports its live supported subset, and unavailable operations fail closed.
Tool selection for AI agents
ReMCP publishes selection-oriented descriptions and ships the same decision tree in its operator skill:
native Accessibility/UI Automation → browser DOM/CDP → OCR → coordinates
- Start unfamiliar desktop work with
computer_snapshot; useui_snapshot/ui_find/ui_actionfor native apps. - For Chromium page content use
browser_navigate action=new_tabwhen needed, thenbrowser_snapshot/browser_find/browser_action/browser_waitinstead of desktop coordinates. - Use
type_textfor normal Unicode text in native/focused controls,browser_actionfor Chromium page DOM text, andkeyboardfor shortcuts/navigation keys. - Use
pointeronly when semantic actions cannot express the task; prefer element ids fordrag_drop. GNOME Wayland drag uses the consent-backed Remote Desktop portal rather than unreliable XTEST drag. - Use
wait_for_ui/browser_waitinstead of fixed sleeps. - Use
screenshot_regionfor targeted visual proof andrecord_screenonly for motion/timing. - Use structured document tools instead of automating Office when the request is about file content.
All 40 computer/browser/diagnostic/document tools declare closed top-level input schemas, parameter descriptions, structured output schemas, and MCP read-only/destructive/idempotent/open-world hints.
Why the tool list looks different from other computer-control servers. Security-sensitive configuration remains deliberately narrow, and everything else the alternatives can do has an equivalent here — usually more than one:
What ReMCP adds beyond the usual set: image reads and screenshots that any MCP client can
display, binary transfer in both directions, archive create/extract, wait_for_process_output instead
of polling, line-range replacement, project-wide replace, unified diffs, checksums, trash instead of
deletion, and host resource reporting.
Nothing is gated. There is no approval prompt, no "are you sure", and no mandatory dry run: a tool
call executes with the full rights of the account running the agent — the same trust model as SSH.
Writes replace by default and moves/copies replace the destination. The catastrophic-command
guardrail defaults to block (a matching command is refused before it runs); an operator may choose
warn or allow.
Files are never written to a local history log, so tool arguments and output are not recorded there.
Unrestricted by design
- No per-call approval contour. ReMCP does not add a confirmation dialog before each tool call.
The local runtime's configured roots, command blocklist and command policy still apply, as do the
operating-system permissions of the account running the agent. Within those boundaries,
start_processcan operate services, packages, databases, containers,sudo, git, and other local tools. - Full transfer in both directions.
read_binary/write_binarymove any file,create_archiveandextract_archivemove whole trees, andtake_screenshotshows the desktop. - Optional hardening, explicit security boundaries.
remcp godmode onlifts the roots, the blocklist and the command guardrail for one computer — and only a person at that computer can turn it on; no MCP tool accepts it.allowedRootsandblockedCommandsare empty until an operator configures them.dangerousCommandsdefaults toblock: a matching catastrophic command is refused before it runs;warnlets it run with an advisory note andallowsilences even that. The runtime refuses to start — loudly — ifruntime.jsoncannot be parsed, so configured safety boundaries are never silently dropped. - Crash-resistant. A bad shell, a closed stdin, or a 40 MB line cannot take the runtime down; the agent restarts it if it exits, so a device recovers instead of going quietly offline.
- Outbound-only. Per-device revocable credential, hashed server-side, stored locally with
restrictive permissions. Runtime metadata from a custom server requires an explicit
--trust-runtimedecision. - No local history. Tool arguments and outputs are never written to a log on your computer.
Usage metrics
Both the client and the runtime collect opt-out usage metrics: tool names, durations, outcomes, coarse error classes, session counts, and device health samples. They never include file paths, file contents, command strings, tool arguments, or tool output — the event schema is a whitelist, so those fields have nowhere to travel.
There is no telemetry endpoint and no third-party processor. The runtime emits MCP notifications to the agent, and the agent forwards them over the authenticated WebSocket it already holds to your ReMCP account. No install ping, no postinstall script, no remote feature flags, no A/B assignment.
Development
Both workspaces are plain ESM with no build step. The contract commands (--help, --version,
--print-tools, --describe) work with no dependencies installed, so CI can diff the advertised
tool surface against the published tarball.
License
MIT.
Source: README.md at commit c5a7d75
Tools
0Version history
8- v0.2.79LatestSep 21, 2026
- v0.2.70Sep 21, 2026
- v0.2.62Sep 20, 2026
- v0.2.52Sep 20, 2026
- v0.2.48Sep 20, 2026
- v0.2.47Sep 19, 2026
- v0.2.46Sep 19, 2026
- v0.2.45Sep 19, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declaredRequired10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts