Skip to main content
Glama

FreeRemoteDesktop

Your computer. Your model. Your rules.

A model-neutral, self-hosted Model Context Protocol (MCP) desktop bridge. FreeRemoteDesktop does not operate an LLM, bypass model subscriptions, or promise free tokens. It replaces metered third-party desktop execution with a local tool server. MIT licensed.

One-click Claude Desktop install (MCP Bundle)

Build and install the FreeRemoteDesktop-0.3.0.mcpb bundle using python pack_mcpb.py. Choose this bundle from Claude Desktop's Extensions > Install Extension. Select your approved workspace when prompted. Requires an MCPB host supporting the UV runtime. This package does not embed Python; the host UV runtime manages it. The manifest is validated with @anthropic-ai/mcpb; actual Claude GUI installation has not yet been tested.

Related MCP server: rig-bridge

Engineering Studio and offline operations

  • Zero-model-call engineering recipes: python frd.py recipes, then use python frd.py run git_status --workspace /your/project.

  • Optional local-model Studio: python local_studio.py, then visit http://127.0.0.1:8899 on the computer. Ollama and a tool-capable model required.

  • Live private screen preview and browser actions are disabled by default.

  • Remote ChatGPT bridge uses the official Secure MCP Tunnel with user-supplied credentials and appropriate ChatGPT workspace entitlements.

Read CONNECTIVITY.md for setup and limitations and ROADMAP.md for ship gates.

Quick start

Requirements: Python 3.10+; Windows, macOS or Linux (GUI capture is primarily tested on Windows).

python setup.py plan --client codex
python setup.py install --client codex
python test_product.py

For Claude Desktop:

python setup.py plan --client claude-desktop
python setup.py install --client claude-desktop

Restart the selected client. Invoke desktop_status to confirm. Fresh installations start with zero approved roots; choose one project directory in the dashboard or edit the config. Configuration is created at ~/.freeremotedesktop/config.json, and existing Codex/Claude config is backed up before editing. The installer never silently changes another agent's configuration.

Tools

Tool

Default

desktop_status

enabled

list_directory

enabled within roots

read_text_file

enabled within roots

search_text / read_lines

bounded and enabled within roots

list_job_recipes / job_history

enabled

run_job

requires local allow_jobs permission

search_text / read_lines

enabled within roots and bounded

list_job_recipes / job_history

enabled

run_job

disabled; explicit local permission required

write_text_file

disabled

run_command

disabled; exact command allowlist

capture_screen

disabled; requires Pillow

gui_click / gui_type / gui_hotkey

disabled; requires PyAutoGUI

browser_navigate / browser_snapshot / browser_screenshot / browser_click / browser_fill

disabled; Playwright + hostname allowlist; click also requires allow_gui

Set the exact approved workspace paths and enable capabilities locally by editing ~/.freeremotedesktop/config.json. The user must explicitly opt in for every dangerous capability. Avoid adding sensitive paths to roots. File-name checks are not a DLP solution.

Optional dependencies:

python -m pip install pillow pyautogui playwright
python -m playwright install chromium  # optional if Google Chrome is installed

The normal read-only installation has zero third-party Python dependencies.

Offline mode — zero AI inference calls

The built-in frd.py CLI runs locally with Python and no model, API key or chatbot:

python frd.py recipes
python frd.py status
python frd.py run git_status --workspace /absolute/path/to/repository
python frd.py run python_compile --workspace /absolute/path/to/project
python frd.py history

Opt in with allow_jobs: true in your local permission configuration, and set the approved root to the project. python_tests separately requires allow_test_execution: true because tests execute project-defined code.

To run a deterministic recipe continuously without invoking any model:

python frd.py schedule git_status --workspace /absolute/path/to/repository --every-seconds 3600

This foreground scheduler runs until interrupted; it is not a persistent OS service. No AI-generated changes or new instructions occur in offline mode. Workflow receipts are stored in ~/.freeremotedesktop/jobs.jsonl.

Token-efficient MCP retrieval

Use search_text to return up to 50 relevant line previews rather than entire files, and read_lines for exact 1–150-line windows. All use the approved root policy, skipping known sensitive filename patterns. This reduces irrelevant context, not the per-token rate charged by an AI provider.

HTTP mode (local integration only)

# set FRD_BEARER_TOKEN to a strong, random secret using your OS secure environment settings
python server.py --transport http --port 8765

The HTTP listener binds 127.0.0.1 only, requires bearer authentication, and is not a production remote MCP deployment. Never publicly proxy it as-is. A remote deployment needs OAuth, per-device user authentication, hardened host/origin and network controls, token rotation, TLS, abuse prevention, and an audit review.

Client/platform matrix

  • Codex and Claude Desktop: supported via STDIO installer.

  • Other STDIO MCP agents: configure command python, args /absolute/path/server.py.

  • Claude web/mobile: needs an authenticated remote HTTPS MCP gateway; not supplied yet.

  • ChatGPT: remote MCP connector availability and write tools depend on plan; not supplied yet.

  • @FreeRemoteDesktop: availability depends on the host client's tool/plugin naming UI.

  • Computer vision: capture_screen returns image bytes when enabled; host client must support rendering or consuming them.

Security model

No privileged agent, daemon, unattended background service, or public endpoint installed. Writes and control are opt-in. Protected filename/extension denylist, configured roots, output/timeout caps, command exact-match allowlist, explicit overwrite flag, and JSONL audit trail. These are protections, not a sandbox. Run under a low-privilege OS user. Do not use on shared machines without additional OS account separation. GUI and browser tools can expose confidential information; enable only with supervision. No telemetry sent to Efficient Labs or any third party by this package.

Architecture

MCP client -> STDIO transport -> policy-gated tools -> local computer
                           \-> optional authenticated loopback HTTP

Current release status

Developer preview v0.3.0; not ready for public production. Remote authentication, visual UI, full screen-streaming, per-action approvals, machine-level integration tests, signed installers, packaging, cross-platform CI and public vulnerability review remain to be implemented and verified.

License

MIT. Copyright 2026 Efficient Labs contributors.

Available Tools

19 tools
browser_clickB
Destructive

Click browser element by CSS selector; requires gui+browser capabilities

Inputs: selector (required).

browser_fillB
Destructive

Fill a non-password browser form field by CSS selector; requires browser+GUI opt-in

Inputs: text (required), selector (required).

browser_navigateA
Read-only

Open allowlisted HTTPS URL in persistent headless browser

Inputs: url (required).

browser_screenshotB
Read-only

Capture the current browser viewport as an image

Inputs: no named parameters.

browser_snapshotA
Read-only

Read the visible browser page text

Inputs: no named parameters.

capture_screenA
Read-only

Capture primary desktop as PNG; requires explicit opt-in

Inputs: no named parameters.

desktop_statusB
Read-only

Return desktop hostname, roots, and enabled capabilities

Inputs: no named parameters.

gui_clickB
Destructive

Click primary desktop screen coordinates; requires explicit opt-in

Inputs: x (required), y (required).

gui_hotkeyB
Destructive

Press an allowlisted keyboard shortcut, requires explicit GUI opt-in

Inputs: keys (required).

gui_typeA
Destructive

Type short text into current focused GUI element, requires explicit local GUI opt-in

Inputs: text (required).

job_historyC
Read-only

List receipts for recent local deterministic jobs

Inputs: limit.

list_directoryA
Read-only

List up to 200 entries in a permitted folder

Inputs: path (required).

list_job_recipesC
Read-only

List deterministic workflows that make zero model calls

Inputs: no named parameters.

read_linesB
Read-only

Read at most 150 numbered lines of a scoped text file

Inputs: end (required), path (required), start (required).

read_text_fileA
Read-only

Read a UTF-8 file within configured size limits

Inputs: path (required).

run_commandB
Destructive

Run only an exact allowlisted shell-free command; disabled by default

Inputs: cwd (required), command (required), timeout_seconds.

run_jobB
Destructive

Execute a locally approved, deterministic workspace workflow; requires allow_jobs

Inputs: recipe (required), workspace (required).

search_textB
Read-only

Search bounded project files locally and return concise line previews

Inputs: path (required), query (required).

write_text_fileA
Destructive

Write a UTF-8 file; disabled by default; no overwrite without explicit flag

Inputs: path (required), text (required), overwrite.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 19 tools

    Disambiguation4/5

    Most tools target clearly distinct resources or capability areas: jobs, filesystem, command execution, GUI, and browser. The main possible confusion is read_text_file versus read_lines, and to a lesser extent capture_screen versus browser_screenshot, but their descriptions make the contexts reasonably clear.

    Naming Consistency4/5

    Names are predominantly snake_case and action-oriented, with clear namespaced prefixes for GUI and browser operations. Minor deviations such as job_history and desktop_status use noun-first phrasing, but the overall convention remains readable and predictable.

    Tool Count4/5

    Nineteen tools is somewhat large, but the server covers several distinct capability families: jobs, filesystem, command execution, desktop GUI, and browser automation. Each tool appears to earn its place within those areas rather than being redundant bloat.

    Completeness4/5

    The surface covers core workflows for file reading/writing/listing/searching, command execution, job running/history, screen capture, GUI input, and browser interaction. Some gaps exist, such as no explicit file delete/move operations and limited browser navigation/history controls, but agents can generally work around them or the omissions are consistent with the safety-first design.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      A local-first MCP server that enables AI-assisted coding through workspace-scoped tools for file reading/editing, command execution, jobs, Git, LSP, media, browser, and desktop workflows. It enforces OAuth, workspace ACL, trust policies, and file/secret guards so owners can safely grant inspect, edit, or trusted capabilities.
      559 npm
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables Windows users to securely bridge compatible cloud LLM MCP services to local applications, allowing discovery and per-app authorization so approved desktop apps can be started or closed via MCP tool calls. It blocks high-risk system tools and stores connection tokens with Windows DPAPI encryption.
      6
      Apache 2.0
    • F
      license
      Not graded
      quality
      A
      maintenance
      Enables web-based AI chat clients and local IDEs to securely operate a user's own machine through an OAuth-gated MCP endpoint, covering file read/write/edit, whitelisted shell execution, search, read-only Git, SQLite, browser automation, DevTools debugging, background tasks, localhost fetching, ports, clipboard, notifications, and Postman control. Its 38 tools are governed by configurable allowed folders, a strict command whitelist, rate limits, and caller blocking, so remote AI assistants get scoped access without unrestricted shell privileges.
      -