Allows sending emails via Gmail, including automated reports, notifications, and file attachments from workers and templates.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@io.github.jarmstrong158/Conductor Run my metrics script every night at 8:30 PM and email me the report"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Claude's hands for local automation — with a web dashboard for the humans who watch it.
Conductor gives Claude direct, persistent control of a local task runner. Tell Claude what you want automated; it creates the scheduled workers, builds multi-step pipelines, wires up email reports, fires test runs, and reads back the logs when something fails — all through conversation. A web dashboard at 127.0.0.1:5000 runs alongside it for humans who want to peek at status, click pause, or hand-edit a worker.
Originally built to automate warehouse reporting workflows (the daily ShipExec metrics pull) and now general-purpose: any Python / batch / shell script, any schedule, any chain.
The MCP server lives in this repo (
server.py) — the thin layer that exposes Conductor's REST API as Claude tools. It's bundled and auto-registered on install, so most users won't need to touch it directly. The separate conductor-mcp repo is deprecated — it holds an older copy without the auto-launch race protection.
Conductor registers itself as an MCP server in Claude Desktop on first launch. After restarting Claude Desktop once, Claude has 21 tools for full control:
Example conversation:
You: Run my metrics script every night at 8:30 PM and email me the report
Claude: I'll set that up using the Run + Email template. (creates the worker, configures the schedule, wires up Gmail, fires it to test) Done — worker "Daily Metrics Report" is live. Check your email for the test run.
You: That uptime check keeps failing. What's going on?
Claude: (pulls the last 10 runs, reads the error logs) The site returned a 503 three times in the last hour. The SSL certificate expired yesterday. Here's the full error from the last run...
You: Chain my backup script and cleanup script together. Run backup first, then cleanup after it finishes. Every day at 2 AM.
Claude: *(creates a chain with stage 0 = backup, stage 1 = cleanup, cron schedule "0 2 * * ") Chain "Nightly Maintenance" created with 2 steps. Backup runs first, cleanup runs after it succeeds.
How it works:
Install Conductor (Windows installer or from source)
Conductor writes its MCP entry to Claude Desktop's config on first launch
Restart Claude Desktop once
Claude now controls Conductor through natural language — create workers, build chains, fire tasks, check logs, send emails
Related MCP server: Self-hosted MCP server for Claude
Claude-Controlled — 21 MCP tools let Claude create workers, chains, groups, templates, and more. Non-technical users can automate anything through conversation.
Flexible Scheduling — Fixed times (09:00, 14:30), intervals (2h 30m), or cron expressions (0 9 * * 1-5 with plain-English preview).
Task Support — Python (.py), batch (.bat, .cmd), and shell (.sh) scripts. Selenium and GUI scripts run in a visible terminal window via new_console.
Built-in Email — configure Gmail once, then any template or worker can send emails. Run + Email template for automated reports. Folder Watcher emails files on arrival. Uptime Check sends DOWN alerts. Worker notifications on success/failure.
Task Chains — multi-step pipelines with parallel execution. Same stage number = run in parallel. Stop-on-failure toggle.
Worker Groups — collapsible named groups for organization. Bulk pause/delete per group.
Run History — per-worker/chain history with status, duration, and error details. Colored dots show last run status at a glance.
Built-in Templates — Folder Backup, File Cleanup, Folder Watcher, Uptime Check, Open URL, Run + Email. Generated scripts are stdlib-only and self-contained.
Per-worker Environment Variables — inject KEY=VALUE pairs into subprocess environments.
Worker Timeout — kill and log workers that run over a set number of minutes.
Email Notifications — per-worker/chain email alerts: Always, On Failure, or On Success.
Import / Export — portable JSON snapshot of all workers, chains, and groups.
Saved Profiles — save and load named worker configurations.
Auto-start on Login — one-click Registry Run key install. No admin required.
Auto-update Check — modal dialog when a newer release is available.
System Tray Icon — right-click for Open Dashboard or Stop.
AI Error Analysis — send error logs to Claude for diagnosis directly in the dashboard.
Persistent State — SQLite database. Workers and chains restore on restart.
Download and run Conductor_Setup.exe from the latest release.
Requires Python 3 on the machine (see note below) — Conductor runs your .py workers with it
Installs to %AppData%\Conductor — no admin/UAC required
Adds Start Menu shortcut and optional desktop shortcut
Optional auto-start at login
Uninstaller included
Python is required for Python workers. Conductor itself ships as a self-contained executable, but it runs your
.pyscripts with a real interpreter found on your system (thepylauncher,PATH, or the Windows registry). If none is found, workers fail loudly with instructions — they are never reported as successful. SetCONDUCTOR_PYTHONto a full path to pin a specific interpreter..bat/.cmd/.shworkers do not need Python.
Python 3.10+
git clone https://github.com/jarmstrong158/conductor.git
cd conductor
pip install -r requirements.txt
python launch.pyThe dashboard opens at http://127.0.0.1:5000. Press Ctrl+C to stop.
.\build.batForces a full rebuild:
.\build.bat --rebuildOutput: Output\Conductor_Setup.exe. Requires Inno Setup.
.py)Scripts run as subprocesses:
if __name__ == "__main__":
print("Task executed!").bat, .sh, .cmd)Executed as subprocesses. The worker's output directory (if set) is used as the working directory.
Type | Format | Example |
Fixed |
|
|
Interval |
|
|
Cron | 5-field crontab |
|
Chains run multiple scripts in sequence. Each step has a stage number — steps with the same stage run in parallel, stages execute in order. Stop on failure halts the chain when any step fails.
Stage 0: backup.py ──┐
Stage 0: cleanup.py ──┤ (both run at once)
↓
Stage 1: report.py (runs after both finish)Template | What it does | Email capability |
Folder Backup | Copy folder, keep N backups | Summary email |
File Cleanup | Delete old files by pattern | Summary email |
Folder Watcher | Move/email files by extension | Per-rule: move, email, or both |
Uptime Check | Monitor URL, log status | Alert email on DOWN |
Open URL | Open URL in browser | — |
Run + Email | Run script, email output file | Sends output as attachment |
All generated scripts use Python stdlib only.
conductor/
├── launch.py # Entry point — Flask, browser, tray, MCP registration
├── app.py # Flask backend + APScheduler + SQLite
├── server.py # MCP server for Claude Desktop
├── CLAUDE.md # Context file for Claude Code / Desktop
├── static/
│ └── index.html # Frontend — HTML + CSS + JS (no frameworks)
├── tasks/
│ └── example_task.py
├── templates/
│ └── generated/ # Auto-generated template scripts
├── build.bat # One-click installer build
├── build_icon.py # Generates conductor.ico
├── conductor.spec # PyInstaller spec
├── installer.iss # Inno Setup script
└── conductor.db # SQLite database (auto-created)Layer | Technology |
Backend | Python 3, Flask |
Scheduling | APScheduler (BackgroundScheduler + MemoryJobStore) |
Persistence | SQLite (WAL mode) |
Frontend | Vanilla JS, single HTML file |
AI Integration | Claude via MCP (21 tools) + Anthropic API (error analysis) |
The debug log includes an Analyze Errors button. When ERROR entries are present, click it to send them to Claude for diagnosis. Requires an Anthropic API key in .env:
ANTHROPIC_API_KEY=sk-ant-...Example — before / after:
Raw error in the debug log:
[ERROR] worker "Daily Metrics Report" exit code 1
Traceback (most recent call last):
File "C:\scripts\metrics.py", line 142, in <module>
driver.find_element(By.ID, "report-table").click()
File ".../selenium/.../webdriver.py", line 830, in find_element
raise NoSuchElementException(message)
selenium.common.exceptions.NoSuchElementException: Message: no such element:
Unable to locate element: {"method":"css selector","selector":"[id="report-table"]"}Claude's diagnosis (one click later):
The script is failing on a
find_elementcall before the page has finished loading — Selenium is racing the DOM. The element#report-tableis rendered after an XHR completes. Two fixes, in order of preference:
Wrap the lookup in a
WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.ID, "report-table")))so it polls until the element exists.If you don't want to import the wait helpers, a
time.sleep(2)before the click will work but is brittle. The traceback shows this happened on the first run after a ShipExec UI change yesterday — they may have also renamed the element. Verify the ID is stillreport-tablein DevTools before adding the wait.
Click 📧 Email in the header to configure Gmail credentials. Requires a Gmail App Password (2-Step Verification must be enabled first). Credentials are stored locally in .env and never transmitted except to Gmail's SMTP server.
Once configured, all templates and worker notifications can send email.
Method | Path | Purpose |
|
| List all workers |
|
| Register worker(s) |
|
| Update worker |
|
| Toggle pause/resume |
|
| Fire immediately |
|
| Run history |
|
| Assign to group |
|
| Delete worker |
|
| Pause all workers |
|
| Delete all workers |
|
| List all chains |
|
| Create chain |
|
| Update chain |
|
| Toggle pause/resume |
|
| Fire immediately |
|
| Run history |
|
| Delete chain |
|
| List groups |
|
| Create group |
|
| Delete group |
|
| List profiles |
|
| Save profile |
|
| Load profile |
|
| Delete profile |
|
| Create from template |
|
| Export all as JSON |
|
| Import from JSON |
|
| Email configuration |
|
| Auto-start status |
|
| Install auto-start |
|
| Remove auto-start |
|
| Check for updates |
|
| Log entries |
|
| Scheduler + database status |
|
| Native file picker |
MIT
Check GitHub for a newer version of Conductor.
Inputs: no named parameters.
Create a new task chain. Steps run sequentially by default. Assign same stage number to multiple steps to run them in parallel. Stage numbers are integers 0-99.
Inputs: name (required), steps (required), sched_type (required), sched_value (required), +3 more.
Create a new worker group.
Inputs: name (required).
Register a new scheduled worker. sched_type: 'fixed' (comma-separated times like '09:00,14:30'), 'interval' (like '2h 30m' or '1h'), or 'cron' (like '0 9 * * 1-5'). timeout_minutes=0 means no timeout. env_vars is KEY=VALUE lines.
Inputs: name (required), task_path (required), sched_type (required), sched_value (required), +7 more.
Create a worker using a built-in template. Template types: folder_backup (source, dest, keep, summary_email), file_cleanup (folder, pattern, days, summary_email), folder_watcher (watch, rules as [{ext, dest, email_to}]), uptime_check (url, log_file, alert_email), open_url (url), run_and_email (script_path, output_file, email_to). Generated scripts use stdlib only.
Inputs: name (required), config (required), sched_type (required), sched_value (required), +1 more.
Delete ALL workers and chains. Irreversible. Use with caution.
Inputs: no named parameters.
Delete a chain and all its steps by ID.
Inputs: chain_id (required).
Delete a group by ID. Unassigns all members but does not delete them.
Inputs: group_id (required).
Delete a worker by ID. Removes from scheduler and database.
Inputs: worker_id (required).
Export all workers, chains, chain steps, and groups as a JSON snapshot. Use for backup or migration.
Inputs: no named parameters.
Get the last 10 run history entries for a chain.
Inputs: chain_id (required).
Check if email credentials are configured. Returns has_credentials (bool) and the sender email address. Use this before any email-related operation to verify setup. If not configured, prompt the user for their Gmail address and App Password.
Inputs: no named parameters.
Get debug log entries. Returns entries since a given offset (use 0 for all). Log levels: INFO, OK, FIRE, MANUAL, ERROR, PAUSE, DELETE. Max 500 entries in buffer (oldest drop off).
Inputs: since.
Check Conductor's scheduler and database status.
Inputs: no named parameters.
Get the last 10 run history entries for a worker. Returns triggered_at, trigger_type, success, duration_ms, error_msg.
Inputs: worker_id (required).
List all task chains. Returns id, name, schedule, steps with stage numbers, stop_on_failure, paused state, next trigger, last run status.
Inputs: no named parameters.
List all worker groups. Groups are collapsible collections of workers and chains in the dashboard.
Inputs: no named parameters.
List all workers and chains in Conductor. Returns id, name, task_path, schedule, paused state, next trigger time, remaining runs today, last run status, and group assignment for each.
Inputs: no named parameters.
Pause all workers at once.
Inputs: no named parameters.
Toggle pause/resume for a worker by ID. If paused, resumes it. If running, pauses it.
Inputs: worker_id (required).
Fire a chain immediately outside its schedule. Logged as MANUAL trigger.
Inputs: chain_id (required).
Fire a worker immediately outside its schedule. Logged as MANUAL trigger type.
Inputs: worker_id (required).
Save Gmail credentials for email notifications and templates. Requires a Gmail address and a Gmail App Password (not the regular password). The user must have 2-Step Verification enabled on their Google account first, then generate an App Password at myaccount.google.com/apppasswords.
Inputs: email (required), password (required).
Update an existing worker by ID. All fields optional except name and task_path which are required.
Inputs: name (required), task_path (required), worker_id (required), env_vars, +9 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 24 tools
Each tool has a clearly distinct purpose, with worker, chain, group, and system operations cleanly separated. Parallel tools for workers vs chains are explicitly named (e.g., run_worker_now vs run_chain_now), preventing misselection.
Most tools follow a consistent verb_noun pattern in snake_case, with verbs like list, create, delete, get, run. Minor deviations: 'delete_all_workers' actually deletes chains too (misleading name), and 'run_worker_now' includes a 'now' suffix not present in 'run_chain_now' (though that is also used). Overall predictable.
At 24 tools, this sits in the borderline range (16-25) and feels somewhat heavy. The domain is complex (workers, chains, groups, settings, admin), so each tool has a purpose, but the count could be streamlined by combining some operations (e.g., pause_all_workers and delete_all_workers).
Worker lifecycle is fully covered with list, create, update, delete, pause, run, history, and bulk operations. However, chains lack an update operation and an individual pause/resume toggle, which is a notable gap. Groups also lack update, but that is less critical. Agents can create and run chains but cannot modify them without deleting and recreating.
Persistent context for Claude. Your AI always knows your projects and next actions across sessions.
Work on your own computers from Claude or ChatGPT: run commands, edit and search files.
Build agents to automate any background task. Works with your ChatGPT/Claude subscription.
Your AI Agent's Infrastructure Layer. Connect Claude, Copilot, Codex, or ChatGPT to 200+ managed open source services. Start databases, pipelines, and applications through natural language.
