Warp Command Runner MCP server
2026년 11월 1일 커밋로컬 채팅 AI가 MCP를 통해 macOS에서 터미널 명령을 실행하고, 출력을 캡처하며, 파일, SSH 및 템플릿을 관리할 수 있도록 지원합니다.
다른 이름 M-Pineapple/warp-command-runner
- 스타
- 18
- Tools
- 40
- 다운로드, 30일
- —
- 최신 버전
- —
- 마지막 커밋
- 2026년 11월 1일
- 라이선스
- MIT
Warp Command Runner MCP란?
로컬 채팅 AI가 MCP를 통해 macOS에서 터미널 명령을 실행하고, 출력을 캡처하며, 파일, SSH 및 템플릿을 관리할 수 있도록 지원합니다. 40개 도구를 제공합니다. 예: execute_command, execute_with_auto_retrieve, execute_pipeline.
프로젝트 README에서 생성된 요약
Warp Command Runner MCP server 정보
이 MCP server는 Claude, ChatGPT 또는 Warp Agent와 같은 데스크톱 클라이언트를 사용하는 개발자가 macOS에서 채팅 AI에 실제 터미널을 제공할 수 있게 합니다. 모델이 대화 중에 직접 명령을 실행하고, 파일을 관리하며, SSH 연결을 처리할 수 있습니다. stdio를 통해 모든 로컬 MCP host와 연동되지만, 특히 Warp 터미널과 통합되도록 설계되어 5개의 특화된 도구로 명령을 활성 탭에 시각적으로 라우팅할 수 있습니다.
사용자는 중단 또는 계속 진행과 같은 특정 실패 모드를 포함한 명령 파이프라인을 통해 복잡한 워크플로우를 관리할 수 있으며, 반복적인 작업을 위해 변수 치환이 가능한 템플릿을 사용할 수 있습니다. 또한 이 server는 장시간 실행되는 프로세스를 위한 출력 스트리밍을 지원하며 Docker, Node, Git과 같은 도구에 대한 환경 인텔리전스를 제공합니다. 모바일 앱이나 웹 브라우저를 사용하는 사용자를 위해, HTTP listener와 사용자가 관리하는 HTTPS 터널을 사용하는 선택적 원격 모드도 제공합니다.
활용 사례
- 1터미널 명령 실행개발자가 AI에게 특정 shell 명령을 실행하고 그 결과 출력을 캡처하도록 요청할 수 있습니다.
- 2복잡한 빌드 파이프라인 자동화AI에게 프로젝트 빌드 및 테스트와 같이 여러 단계를 연결하도록 지시하고, 오류 발생 시 처리 방법을 정의할 수 있습니다.
- 3SSH를 통한 원격 서버 관리AI 클라이언트가 통합된 SSH 기능을 사용하여 원격 호스트에서 작업을 수행할 수 있습니다.
프로젝트의 README를 바탕으로 작성되었습니다. 모든 활용 사례는 해당 내용의 인용문과 대조하여 확인합니다.
Warp Command Runner MCP 도구 40
README에서 감지됨execute_commandexecute_with_auto_retrieveexecute_pipelineexecute_with_streamingsave_templaterun_templatelist_templatesdelete_templateget_command_outputpreview_commandsuggest_commandlist_recent_commands
| execute_command | — | |
| execute_with_auto_retrieve | — | |
| execute_pipeline | — | |
| execute_with_streaming | — | |
| save_template | — | |
| run_template | — | |
| list_templates | — | |
| delete_template | — | |
| get_command_output | — | |
| preview_command | — | |
| suggest_command | — | |
| list_recent_commands | — |
도구 40개 모두 보기도구 수 줄이기
self_checkcopy_to_clipboardread_from_clipboardset_notification_preferenceget_environment_contextexecute_and_parsecapture_environmentdiff_environmentsave_workspace_profileload_workspace_profilelist_workspace_profilesdelete_workspace_profileopen_terminal_tabsend_to_sessionlist_sessionsclose_sessioncleanup_sessionscheck_interactiveadd_file_watchremove_file_watchlist_file_watchesssh_executesave_ssh_profilelist_ssh_profilesdelete_ssh_profilefocus_warp_sessionemit_warp_eventshell_shim_status
| self_check | — | |
| copy_to_clipboard | — | |
| read_from_clipboard | — | |
| set_notification_preference | — | |
| get_environment_context | — | |
| execute_and_parse | — | |
| capture_environment | — | |
| diff_environment | — | |
| save_workspace_profile | — | |
| load_workspace_profile | — | |
| list_workspace_profiles | — | |
| delete_workspace_profile | — | |
| open_terminal_tab | — | |
| send_to_session | — | |
| list_sessions | — | |
| close_session | — | |
| cleanup_sessions | — | |
| check_interactive | — | |
| add_file_watch | — | |
| remove_file_watch | — | |
| list_file_watches | — | |
| ssh_execute | — | |
| save_ssh_profile | — | |
| list_ssh_profiles | — | |
| delete_ssh_profile | — | |
| focus_warp_session | — | |
| emit_warp_event | — | |
| shell_shim_status | — |
구성
WCR_CODESIGN_IDENTITYWCR_HOME
| 이름 | 설명 | 유형 |
|---|---|---|
| WCR_CODESIGN_IDENTITY | — | |
| WCR_HOME | — |
자동 검사
2026년 11월 13일에 실행됨전체 보고서 →아직 인증되지 않았습니다. 서버는 80점 이상의 점수, 심각한 결함 없음, 그리고 검사에 충분한 데이터를 갖추어야 합니다. 검사 방식 · 점수를 높이기 위해 수정할 항목
- 소스 저장소 연결 및 접근 가능통과
- 오픈 소스 라이선스 (OSI)통과
- 최근 1년 내 커밋 또는 릴리스통과
- 패키지 이름이 인기 패키지와 유사하지 않음검사되지 않음
- 원격 엔드포인트가 HTTPS 사용검사되지 않음
- 파괴적인 도구에 라벨 표시됨검사되지 않음
- 모델에 대한 숨겨진 지침 없음통과
- 패키지 및 해당 종속성에 중요한 보안 권고 없음검사되지 않음
README
GitHub에서 보기Warp Command Runner
Give any chat AI a real terminal. You ask in Warp, Claude Desktop, ChatGPT desktop, or any other MCP host. The model types the command into your Warp tab, captures the output, and tells you what happened. Forty tools: command execution, project setups, file watching, SSH, clipboard, environment intelligence. macOS, Swift, open source.
This is for people who don't live in Cursor or Claude Code. If you already chat with Grok, ChatGPT, Claude, or Gemini from a desktop app (especially Warp's agent panel), add this MCP and that chat can read your files and run commands on your machine.
Built for Warp Terminal. The five most powerful tools route commands visibly into your active Warp tab. Register the same binary with as many MCP hosts as you want — the server speaks standard MCP over stdio and does not care which model is calling.
Can any cloud AI use this? Any local MCP host can, over stdio. Phone apps and websites need remote MCP: you run --http and publish HTTPS with a tunnel you own. Guide: docs/REMOTE.md. Matrix: docs/COMPATIBILITY.md.
What's new in v8.0.2
Release 8.0.2 builds with swift-sdk 0.12.1 (no local patch) and ships a committed Package.resolved so a fresh clone resolves the same versions. Remote --http pairing from 8.0.1 still applies: a one-time code shown on the Mac authorizes a new client. Remote-mode users should update and delete ~/.warp-command-runner/oauth-store.json to re-pair. Details: docs/REMOTE.md.
The data folder is ~/.warp-command-runner unless you set WCR_HOME (see Data directory).
Quick start
You need macOS 13 or later, Swift 6.0+ (Xcode 16+), and a local MCP host such as Warp Agent or Claude Desktop.
git clone --branch v8.0.4 --depth 1 https://github.com/M-Pineapple/warp-command-runner.git
cd warp-command-runner
./build.sh
./build.sh resolves packages, applies the required swift-sdk patch, builds the release binary, and wraps it in .build/release/warp-command-runner.app.
Point your host at the binary inside that bundle. For Warp Agent, merge this into ~/.warp/.mcp.json and replace the path with yours:
{
"mcpServers": {
"warp-command-runner": {
"command": "/absolute/path/to/warp-command-runner/.build/release/warp-command-runner.app/Contents/MacOS/warp-command-runner",
"args": []
}
}
}
Restart the host. Ask it to run swift --version. That uses execute_pipeline and needs no Accessibility grants.
Data directory
Config, command history, templates, and SSH profiles live in ~/.warp-command-runner. Set WCR_HOME to use a different folder. The value must be an absolute path or start with ~/. Relative values are ignored. macOS ignores a process-level HOME= for FileManager.homeDirectoryForCurrentUser, so WCR_HOME is the supported override. The folder is created with owner-only permissions (0700). ConfigManager uses the same resolution.
{
"mcpServers": {
"warp-command-runner": {
"command": "/absolute/path/to/warp-command-runner/.build/release/warp-command-runner.app/Contents/MacOS/warp-command-runner",
"args": [],
"env": {
"WCR_HOME": "~/wcr-test"
}
}
}
}
When WCR_HOME is set to a valid path, the server does not copy ~/.claude-command-runner into that folder.
An unsigned build is enough for the 34 non-keystroke tools. The five Warp-routing tools need a signed .app in /Applications/. Host snippets, signing, and the Sequoia recipe are under Installation. Phone and website hosts need --http plus your own HTTPS tunnel. See docs/REMOTE.md.
What's new in v8.0.0 — remote MCP
Opt-in Streamable HTTP so Grok, ChatGPT, and Claude can call this Mac from a phone or a website. You create the public HTTPS URL (your Cloudflare tunnel, your Tailscale Funnel, or your reverse proxy). This project does not host a relay.
warp-command-runner --httplistens on127.0.0.1only (default port 8741)- OAuth 2.1 with PKCE and Dynamic Client Registration
- Warp-routing (keystroke) tools stay off for remote callers; use
execute_pipeline --remote-doctorand--install-agentfor a login LaunchAgent
Local stdio is unchanged. Details: docs/REMOTE.md.
What's new in v7.0.0 — rebrand
Formerly Claude Command Runner. Same engine, host-agnostic name:
- Product, binary, bundle ID, and config dir renamed to Warp Command Runner (
warp-command-runner,~/.warp-command-runner) - Existing
~/.claude-command-runnerdata is copied on first launch (the old folder is left in place) - MCP
serverInfoname isWarp Command Runnerso every host lists it that way - Config snippets for Warp, Claude Desktop, ChatGPT desktop, Cursor, VS Code, and a generic stdio host
- Honest compatibility doc: stdio MCP works everywhere a local host exists. Remote MCP is opt-in in v8 (
docs/REMOTE.md).
v6.x history (Warp deeplinks, OSC 777, dual-consumer Warp Agent, 40 tools) is unchanged — see CHANGELOG.md.
Overview
Warp Command Runner is an MCP server. One binary, any MCP client:
- Execute terminal commands from a conversation
- Chain commands with pipelines and failure modes
- Stream output for long builds
- Save and reuse command templates with variables
- Auto-capture output with intelligent timing
- Track command history
- Read/write the macOS clipboard
- Probe environment context (git, venv, Docker, Node)
- Parse command output into structured JSON
- Manage workspace profiles (optionally as Warp launch configs)
- Open Warp tabs via
warp://deeplinks and send commands to the active tab - Watch files and trigger commands on changes
- Execute commands on remote hosts via SSH
- Surface status into Warp as OSC 777
warp://cli-agentevents - Optional shell shim: preexec / command-finished events over a Unix socket
🧭 Which app should I register this with?
The protocol is MCP. The value depends on whether the host is local and whether Warp is your terminal. Details in docs/COMPATIBILITY.md.
| Host | Config | Recommended? |
|---|---|---|
| Warp Agent (Grok, Claude, GPT, Gemini — whatever Warp is set to) | ~/.warp/.mcp.json |
Yes — best fit. See docs/WARP_AGENT.md |
| Claude Desktop | ~/Library/Application Support/Claude/claude_desktop_config.json |
Yes |
| ChatGPT desktop (Connectors / Developer Mode) | host MCP settings; snippet in config/chatgpt-mcp.json |
Yes, if your plan exposes local MCP |
| VS Code / Continue / Cline / Windsurf | their MCP settings; see config/ |
Optional |
| Cursor | ~/.cursor/mcp.json |
Optional — Cursor already has a terminal |
| Claude Code | ~/.claude.json |
Niche — it already has Bash |
| Browser / phone chats (chatgpt.com, grok.com, claude.ai) | custom connector URL | Optional — needs v8 --http plus your HTTPS tunnel. docs/REMOTE.md |
Quick decision tree
- You use Warp and chat with Grok / ChatGPT / Claude / Gemini inside Warp? → Register in
~/.warp/.mcp.json. That's the whole product. - You use Claude Desktop (or ChatGPT desktop) and want commands visible in Warp? → Register there too. Same binary.
- You use Cursor or Claude Code and want everything in one pane? → You probably don't need this.
- You only use a website or phone chatbot? → Stdio cannot reach that tab. Enable remote MCP (
docs/REMOTE.md) or use a desktop MCP host.
Five of the 40 tools (execute_command, execute_with_auto_retrieve, execute_with_streaming, run_template, send_to_session) are the Warp-routing ones. The rest are ordinary server-side utilities (clipboard, SSH, snapshots, …) that work from any host.
🎯 Key Features
Command Pipelines
Chain multiple commands with intelligent failure handling:
{
"steps": [
{"name": "Build", "command": "swift build", "on_fail": "stop"},
{"name": "Test", "command": "swift test", "on_fail": "continue"},
{"name": "Package", "command": "swift build -c release", "on_fail": "stop"}
]
}
Failure modes:
stop– Halt pipeline on failurecontinue– Log error and proceed to next stepwarn– Show warning and continue
Output Streaming
Real-time output for long-running commands:
{
"command": "swift build -c release",
"update_interval": 3,
"max_duration": 180
}
Perfect for:
- Long compilation processes
- Test suites
- Any command that previously "hung" waiting for output
Command Templates
Save reusable patterns with variable substitution:
// Save a template
{
"name": "swift-release",
"template": "cd {{project}} && swift build -c release",
"category": "Swift Development",
"description": "Build Swift project in release mode"
}
// Run with variables
{
"name": "swift-release",
"variables": {"project": "~/GitHub/MyApp"}
}
Templates are stored in ~/.warp-command-runner/templates.json and persist across sessions.
Smart Auto-Retrieve
The execute_with_auto_retrieve command intelligently detects command types and adjusts wait times:
- Quick commands (echo, pwd): 2-6 seconds
- Moderate commands (git, npm): up to 20 seconds
- Build commands (swift build, make): up to 77 seconds
- Test commands: up to 40 seconds
📊 Why Warp Terminal?
Warp Terminal is the primary integration target. Other terminals work for the basics — Warp uniquely unlocks deeplinks, OSC 777, the native agent panel, and launch configs:
| Feature | Warp | Terminal.app | iTerm2 |
|---|---|---|---|
warp:// deeplinks for tab/window |
✅ | ❌ | ❌ |
| Native MCP agent panel — chat with Grok, ChatGPT, Claude, Gemini in the terminal | ✅ (~/.warp/.mcp.json) |
❌ | ❌ |
| OSC 777 cli-agent event channel for status surfacing | ✅ | ❌ | ❌ |
| Workspace profile → recognized launch config | ✅ (~/.warp/launch_configurations/) |
❌ | ❌ |
| AppleScript-driven new tab + keystroke send | ✅ | ✅ | ✅ |
| Modern UI/UX | ✅ | ⚠️ | ⚠️ |
Output capture (/tmp/<id>.json polling) and the tools that don't touch the terminal (clipboard, SSH, file watch, env snapshots, etc.) work identically across all terminals.
Download Warp from warp.dev. It is free, and the Warp-specific surfaces above need it.
Installation
Prerequisites
- macOS 13.0 or later
- Swift 6.0+ (Xcode 16+)
- At least one local MCP host (Warp Agent, Claude Desktop, ChatGPT desktop, VS Code, …) — not a browser chat tab
- A supported terminal (Warp strongly recommended)
Quick Install
- Clone and build:
git clone https://github.com/M-Pineapple/warp-command-runner.git
cd warp-command-runner
# For the 5 keystroke-routing tools (execute_command, etc.) to work, the build
# must be SIGNED with your code-signing identity. build.sh auto-detects a single
# Apple Development / Developer ID identity; to be explicit (or if you have
# several), export it first — find yours with:
# security find-identity -v -p codesigning
export WCR_CODESIGN_IDENTITY="<your-cert-sha1>" # optional if auto-detect finds one; persist in ~/.zshrc
./build.sh
Only need the 34 non-keystroke tools (incl.
execute_pipeline)? An unsigned build is fine — skip theexport.
./build.sh writes two things: the app bundle .build/release/warp-command-runner.app (use this) and the bare binary .build/release/warp-command-runner. It does not install anything into /Applications/. To use the /Applications/ paths in the snippets below, copy the bundle there yourself:
cp -R .build/release/warp-command-runner.app "/Applications/Warp Command Runner.app"
Or skip the copy and point your host at $(pwd)/.build/release/warp-command-runner.app/Contents/MacOS/warp-command-runner (the 5 keystroke-routing tools need the bundle in /Applications/; see the Sequoia recipe below).
-
Pick your MCP host(s) — you can register the same binary in several. Point at the binary inside the
.appbundle (macOS Sequoia+ needs the Info.plist for TCC prompts on the 5 keystroke-routing tools):A — Warp Agent (
~/.warp/.mcp.json) — Grok, ChatGPT, Claude, Gemini, whichever Warp is set to:{ "mcpServers": { "warp-command-runner": { "command": "/Applications/Warp Command Runner.app/Contents/MacOS/warp-command-runner", "args": [] } } }See
docs/WARP_AGENT.md.B — Claude Desktop (
~/Library/Application Support/Claude/claude_desktop_config.json) — same JSON shape as Warp Agent.C — Cursor (
~/.cursor/mcp.json) — the/Applications/...path contains spaces, so keep it as one quoted JSON string:{ "mcpServers": { "warp-command-runner": { "command": "/Applications/Warp Command Runner.app/Contents/MacOS/warp-command-runner", "args": [] } } }If Cursor reports
spawn /Applications/Warp ENOENT, it split the path on spaces. Runhelper/install-cursor-wrapper.shand pointcommandat~/.local/bin/warp-command-runnerinstead. Seeconfig/cursor-mcp.json.ChatGPT desktop, VS Code, Continue: copy a snippet from
config/ordocs/COMPATIBILITY.md.After
./build.shyou can also point at$(pwd)/.build/release/warp-command-runner.app/Contents/MacOS/warp-command-runnerbefore copying the bundle to/Applications/.Upgrading from v6.0.0–6.0.2? Edit your existing config file and append
.app/Contents/MacOS/warp-command-runnerto the path. The legacy bare-binary path still works for the 34 non-keystroke tools, butexecute_command/execute_with_auto_retrieve/execute_with_streaming/run_template/send_to_sessionwill silently fail without the bundle path. -
Grant Accessibility permission (only required for
send_to_sessionkeystroke injection in v6.0; tab/window opening uses deeplinks and does not require it):- Open System Settings → Privacy & Security → Accessibility
- Click + and navigate to
warp-command-runner/.build/release/ - Press Cmd+Shift+. to reveal the hidden
.buildfolder - Select the
warp-command-runnerbinary and toggle it on
Important: macOS tracks permissions by binary identity. After every rebuild (
./build.sh), you must remove the old entry and re-add the new binary in Accessibility settings.
-
Restart your MCP host(s) (Warp, Claude Desktop, ChatGPT desktop, …).
-
(Optional) Install the shell shim for cleaner block-boundary capture:
helper/install-shim.shSee
helper/shell-shim.zsh/helper/shell-shim.bashfor the implementation. Uninstall withhelper/uninstall-shim.sh.
Linux and containers
The server is built for macOS, but the stdio server also builds and runs on Linux, so registries such as Glama can start it in a container to check it:
docker build -t warp-command-runner .
docker run -i --rm warp-command-runner
On Linux it lists the same 40 tools. The ten that drive Warp or other macOS apps (execute_command, execute_with_auto_retrieve, execute_with_streaming, run_template, send_to_session, open_terminal_tab, focus_warp_session, copy_to_clipboard, read_from_clipboard, add_file_watch) return a "needs macOS" error. execute_pipeline, execute_and_parse, ssh_execute and the history, template and analysis tools work. Remote mode (--http, --install-agent) is macOS only.
Upgrading from a previous version
If you already have a signed install working (TCC permissions granted), upgrading is:
cd warp-command-runner
git pull
# Rebuild with the SAME signing identity you used originally. Without it, build.sh
# falls back to an ad-hoc-signed bundle, macOS sees a new identity, and your
# keystroke (TCC) grants stop applying → error 1002 on execute_command.
# (build.sh auto-detects a single identity; export to be explicit.)
export WCR_CODESIGN_IDENTITY="<your-cert-sha1>" # persist in ~/.zshrc so you don't forget
./build.sh
# Confirm it signed with your cert (NOT adhoc) BEFORE replacing your good bundle:
codesign -dvv .build/release/warp-command-runner.app 2>&1 | grep -E "Authority=Apple|Signature=adhoc"
# Replace the deployed bundle (rm first — cp -R onto an existing .app nests it):
rm -rf "/Applications/Warp Command Runner.app"
cp -R .build/release/warp-command-runner.app "/Applications/Warp Command Runner.app"
Then restart your MCP host. If you upgraded from v6 and kept the same signing certificate, existing TCC grants on com.m-pineapple.claude-command-runner do not transfer to com.m-pineapple.warp-command-runner — re-grant Accessibility / Input Monitoring / Full Disk Access / Automation for the new bundle once. After that, same-cert rebuilds keep the grants.
If you use remote --http mode, delete ~/.warp-command-runner/oauth-store.json after installing 8.0.1 and connect again so the new pairing code is required.
🛡️ macOS Sequoia full setup recipe (the 7 ordered steps)
If
execute_command/execute_with_auto_retrieve/execute_with_streaming/run_template/send_to_sessionfail withosascript is not allowed to send keystrokes (1002)even though you've toggled every panel in System Settings, follow this in order — skipping any step leaves a silent denial somewhere in the chain. The other 34 tools work without any of this;execute_pipelineis a fully-functional substitute if you want to skip the whole TCC saga entirely.This is the empirically-verified recipe from a real 6-hour debugging session. v6.0.3+ ships the bundle infrastructure that makes this possible; v6.0.4 is this documentation pass.
The denial pattern. macOS Sequoia's TCC and sandbox have layered, non-obvious requirements for CLI binaries that drive osascript → System Events → keystroke. The error message is misleading — the actual block usually isn't keystroke permission; it's an earlier preflight check that silently aborts the chain. The five gates, in the order macOS evaluates them:
| Gate | TCC service | What grants it |
|---|---|---|
| 1. Bundle promptability | (n/a — policy) | Bundle in /Applications/, not .build/release/ |
| 2. Bundle identity stable | (n/a — codesign) | Signed with a stable cert (cdhash doesn't drift across rebuilds) |
| 3. Sandbox FDA preflight | kTCCServiceSystemPolicyAllFiles |
Full Disk Access grant on the bundle |
| 4. AppleEvents | kTCCServiceAppleEvents |
Automation → System Events ☑ |
| 5. Keystroke synthesis | kTCCServiceListenEvent / kTCCServicePostEvent |
Input Monitoring + Accessibility |
Step 1 — Have an Apple Development cert (or self-signed Code Signing cert)
If you have a paid Apple Developer account, you already have one (check via security find-identity -v -p codesigning). If not, create a self-signed one:
- Keychain Access → menu Certificate Assistant → Create a Certificate…
- Name:
warp-command-runner, Identity Type: Self Signed Root, Certificate Type: Code Signing - Click Create → Continue through warnings → Done
Export the cert identifier for build.sh to find:
# Get the SHA-1 hash (more reliable than the cert name)
security find-identity -v -p codesigning
# Then in your shell rc (~/.zshrc, ~/.config/fish/config.fish, etc.):
export WCR_CODESIGN_IDENTITY="<the-sha1-hash-from-above>"
Step 2 — Build (creates the signed .app bundle)
./build.sh
build.sh invokes scripts/make-app-bundle.sh, which wraps the CLI in .build/release/warp-command-runner.app/ with a proper Info.plist (CFBundleIdentifier com.m-pineapple.warp-command-runner, the three required NSXxxUsageDescription strings, LSUIElement=true). If WCR_CODESIGN_IDENTITY is set, the bundle is signed with that cert as a unit — stable cdhash across rebuilds.
Verify:
codesign --display --verbose=4 .build/release/warp-command-runner.app | grep -E 'Identifier|TeamIdentifier|CDHash'
codesign --verify --deep --strict .build/release/warp-command-runner.app # should succeed silently
Step 3 — Install the bundle into /Applications/ (CRITICAL)
macOS refuses to prompt for TCC permissions on bundles in .build/release/ or other dev directories. The bundle must live in /Applications/. Copy it:
cp -R .build/release/warp-command-runner.app "/Applications/Warp Command Runner.app"
Verify the signature survived the copy:
codesign --verify --deep --strict "/Applications/Warp Command Runner.app"
Step 4 — Point your MCP config at the /Applications/ path
Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"warp-command-runner": {
"command": "/Applications/Warp Command Runner.app/Contents/MacOS/warp-command-runner",
"args": []
}
}
}
Mirror in ~/.warp/.mcp.json if you use the Warp Agent path.
Step 5 — Reset stale TCC entries for the bundle ID
If you've been struggling with TCC denials previously, your TCC.db likely has stale Denied entries from earlier rebuilds with different cdhashes. Wipe them for the bundle:
for svc in AppleEvents ListenEvent PostEvent Accessibility; do
tccutil reset "$svc" com.m-pineapple.warp-command-runner
done
Each line should print "Successfully reset". If you see "no entries", that's also fine — means TCC had nothing recorded yet.
Step 6 — Grant the three TCC permissions (Full Disk Access is the surprise one)
In System Settings → Privacy & Security, add /Applications/Warp Command Runner.app to each of:
- Full Disk Access — unexpected but mandatory. macOS sandbox does a preflight check for
kTCCServiceSystemPolicyAllFilesbefore allowing osascript to spawn for keystroke chains. Without FDA on the bundle, the sandbox denies before TCC's AppleEvents check ever fires, and you get the misleading "send keystrokes" error. - Input Monitoring — for
kTCCServiceListenEvent/kTCCServicePostEvent(synthetic keystroke generation). - Accessibility — for the
keystrokeAppleEvent action itself.
Each grant requires Touch ID / admin password to confirm. Bundle name appears as "Warp Command Runner" in the panels.
Step 7 — Restart Claude Desktop, trigger once, grant the Automation prompt
⌘Q Claude Desktop, reopen. On your first execute_command, macOS may show one more prompt — Automation → "Warp Command Runner wants to control System Events" — click Allow. After that, it's permanent. Future rebuilds don't reset anything (the cert keeps cdhash stable; the bundle keeps the identity stable).
Warp Command Runner MCP 질문
Warp Command Runner MCP는 어떤 도구를 제공하나요?
40개 도구를 제공합니다. 예: execute_command, execute_with_auto_retrieve, execute_pipeline, execute_with_streaming, save_template.
Warp Command Runner로 AI 클라이언트가 무엇을 할 수 있나요?
MCP host가 macOS에서 터미널 명령을 실행하고, 파이프라인을 연결하며, 출력을 스트리밍하고, 템플릿을 저장하고, 클립보드를 사용하며, SSH 명령을 실행할 수 있습니다.
macOS와 Swift가 필요한가요?
네. macOS 13 이상과 Swift 6.0 이상(Xcode 16 이상)이 필요하며, ./build.sh를 통해 소스에서 직접 빌드해야 합니다.
모든 도구에 코드 서명이 필요한가요?
아니요. 40개의 도구 중 34개는 서명되지 않은 빌드로도 충분합니다. 다만 Warp-routing keystroke 도구 5개는 /Applications에 서명된 앱이 있어야 합니다.
설정 및 명령 기록은 어디에 저장되나요?
설정, 기록, 템플릿 및 SSH 프로필은 ~/.warp-command-runner에 저장됩니다. WCR_HOME을 절대 경로로 설정하면 해당 폴더에 저장됩니다.