Tool Catalog (generated)

Machine-generated signature index for the Leif MCP tools, built from the live FastMCP tool schemas. The exhaustive companion to the curated per-namespace reference pages.

This page is generated from the live FastMCP tool schemas — the parameters and defaults are exactly what the server accepts. It is the exhaustive, never-stale signature index; the curated namespace pages remain the readable guides with prose, gotchas, and worked examples.

`cwa_*` — ConnectWise Automate (RMM)

Find managed computers, run scripts/commands, read history. Note: only saved-script execution (cwa_execute / cwa_run_powershell) returns real stdout; cwa_run_command type 2 always returns Output: “ERR”.

Curated guide: ConnectWise Automate (RMM).

`cwa_search`

Search ConnectWise Automate computers (preferred over cwa_get).

Param	Type	Required	Default	Notes
`name`	`string\|null`	no	—	Substring match on computer name
`condition`	`string\|null`	no	—	Raw OData condition
`page`	`integer`	no	`1`	Page number
`page_size`	`integer`	no	`50`	Items per page

`cwa_get`

Get or list CWA records by entity type / ID.

Param	Type	Required	Default	Notes
`entity_type`	`string`	yes	—	Record type
`id`	`integer\|null`	no	—	Direct ID lookup
`condition`	`string\|null`	no	—	OData condition
`page`	`integer`	no	`1`
`page_size`	`integer`	no	`50`

`cwa_status`

Quick CWA health overview (alerts + offline agents).

Param	Type	Required	Default
`include_alerts`	`boolean`	no	`true`
`include_offline`	`boolean`	no	`true`
`offline_limit`	`integer`	no	`10`

`cwa_execute`

Run a saved CWA library script on a computer (returns real captured output).

Param	Type	Required	Default	Notes
`computer_id`	`integer`	yes	—	Target computer
`script_id`	`integer`	yes	—	Library script ID
`parameters`	`object\|null`	no	—	{string: string} script-variable inputs

`cwa_run_command`

Queue an ad-hoc command. command_type 2 is fire-and-forget (Output always “ERR”).

Param	Type	Required	Default	Notes
`computer_id`	`integer`	yes	—
`command`	`string\|null`	no	—	Convenience command string
`command_type`	`string`	no	`2`	2=Execute, 301=Invoke Script, 22=Update Configs
`shell`	`string`	no	`cmd`
`auto_encode`	`boolean`	no	`true`	Wrap metachars as base64 EncodedCommand
`auto_salt_on_duplicate`	`boolean`	no	`true`	Retry once on 400 Duplicate command

`cwa_run_powershell`

Run ad-hoc PowerShell via the encoded-PS shim — the only path that returns real PS stdout.

Param	Type	Required	Default	Notes
`computer_id`	`integer`	yes	—
`script`	`string`	yes	—	Raw PowerShell (not pre-encoded)
`shim_script_id`	`integer`	yes	—	Library ID of ‘Leif - Run Encoded PowerShell’
`poll_interval`	`number`	no	`3`
`poll_attempts`	`integer`	no	`20`

`cwa_search_scripts`

Search the CWA script library by name or OData condition.

Param	Type	Required	Default	Notes
`name`	`string\|null`	no	—
`condition`	`string\|null`	no	—

`cwa_script_history`

Recent script-run history; DiagnosticMessage carries captured output.

Param	Type	Required	Default	Notes
`computer_id`	`integer`	yes	—
`script_id`	`integer\|null`	no	—	Filter to one script
`limit`	`integer`	no	`10`

`cwa_raw_request`

Raw authenticated CWA API call; never raises on 4xx/5xx.

Param	Type	Required	Default	Notes
`method`	`string`	yes	—	HTTP method
`path`	`string`	yes	—	API path beginning with /
`body`	`object\|null`	no	—
`params`	`object\|null`	no	—

`cwa_probe_command_endpoint`

Probe candidate command-endpoint paths; caches the winner.

Param	Type	Required	Default	Notes
`computer_id`	`integer`	yes	—

`hudu_*` — Hudu (IT Documentation)

IT documentation system of record — companies, assets, articles, passwords, and their relationships. Entity-typed CRUD scoped by company_id; ‘delete’ is usually an archive via hudu_update (action=archive), and hudu_lookup bridges an external integration’s identifier to a Hudu resource and back.

Curated guide: Hudu (IT Documentation).

`hudu_get`

Get or list records by entity type, with rich filtering.

Param	Type	Required	Default	Notes
`entity_type`	`string`	yes	—	company, asset, article, …
`id`	`integer\|null`	no	—	Fetch a single record
`name`	`string\|null`	no	—	Filter by name
`company_id`	`integer\|null`	no	—	Scope to one company — the usual way to narrow assets/articles
`integration_id`	`string\|null`	no	—	Cross-reference an external integration’s identifier
`data`	`object\|null`	no	—	Extra filter payload
`page`	`integer`	no	`1`	Page number
`page_size`	`integer`	no	`25`	Items per page

`hudu_search`

Free-text search across Hudu entities.

Param	Type	Required	Default	Notes
`query`	`string`	yes	—

`hudu_lookup`

Special integration-bridge lookup keyed by lookup_type — map an external system’s identifier to a Hudu resource and back.

Param	Type	Required	Default	Notes
`lookup_type`	`string`	yes	—	Selects the lookup
`company_id`	`integer\|null`	no	—
`integration_id`	`string\|null`	no	—
`integration_slug`	`string\|null`	no	—	External integration slug
`integration_identifier`	`string\|null`	no	—	Identifier within that integration
`resource_type`	`string\|null`	no	—
`resource_id`	`integer\|null`	no	—
`user_id`	`integer\|null`	no	—
`page`	`integer`	no	`1`

`hudu_create`

Create a record. name is required; data carries the rest, scoped by company_id for company-owned entities.

Param	Type	Required	Default	Notes
`entity_type`	`string`	yes	—
`name`	`string`	yes	—	Record name
`company_id`	`integer\|null`	no	—	Scope company-owned entities
`data`	`object\|null`	no	—	Rest of the record fields

`hudu_update`

Update AND archive/unarchive flow through this one tool via action.

Param	Type	Required	Default	Notes
`entity_type`	`string`	yes	—
`id`	`integer`	yes	—
`action`	`string`	no	`update`	update \| archive (soft delete) \| unarchive
`company_id`	`integer\|null`	no	—
`data`	`object\|null`	no	—	Fields to apply when action=update

`hudu_delete`

Hard delete by ID — irreversible. Prefer hudu_update action=archive for anything you might want back.

Param	Type	Required	Default	Notes
`entity_type`	`string`	yes	—
`id`	`integer`	yes	—

`repairshopr_*` — RepairShopr

System of record for tickets, customers, invoices. Entity-typed CRUD plus comments and search.

Curated guide: RepairShopr.

`repairshopr_get`

Get a record by ID or list/filter records of a type.

Param	Type	Required	Default	Notes
`entity_type`	`string`	yes	—	ticket, customer, invoice, …
`id`	`integer\|null`	no	—	Fetch one; omit to list
`filters`	`object\|null`	no	—	Field filters when listing

`repairshopr_create`

Create a record.

Param	Type	Required	Default	Notes
`entity_type`	`string`	yes	—
`data`	`object`	yes	—	Full record payload

`repairshopr_update`

Update a record (only the fields in data).

Param	Type	Required	Default
`entity_type`	`string`	yes	—
`id`	`integer`	yes	—
`data`	`object`	yes	—

`repairshopr_delete`

Delete a record (destructive).

Param	Type	Required	Default	Notes
`entity_type`	`string`	yes	—
`id`	`integer`	yes	—

`repairshopr_comment`

Add a comment to a ticket, with visibility/email control.

Param	Type	Required	Default	Notes
`ticket_id`	`integer`	yes	—
`comment`	`string`	yes	—
`hidden`	`boolean`	no	`false`	true = internal, not customer-visible
`do_not_email`	`boolean`	no	`false`	true = suppress customer email

`repairshopr_search`

Cross-entity free-text search.

Param	Type	Required	Default	Notes
`query`	`string`	yes	—
`search_type`	`string`	no	`all`	Narrow to an entity when known

`quickbooks_*` — QuickBooks Online

Accounting. quickbooks_query is the SQL-like read workhorse; mutations use QBO’s SyncToken concurrency model. IDs are strings.

Curated guide: QuickBooks Online.

`quickbooks_query`

Run a raw QBO SQL-like query (no JOINs; paginate with start_position).

Param	Type	Required	Default	Notes
`query`	`string`	yes	—	e.g. SELECT * FROM Invoice WHERE Balance > ‘0’
`max_results`	`integer\|null`	no	—	Page size
`start_position`	`integer\|null`	no	—	1-indexed offset

`quickbooks_get`

Get a single record by ID or list a type.

Param	Type	Required	Default	Notes
`entity_type`	`string`	yes	—
`id`	`string\|null`	no	—	QBO IDs are strings
`filters`	`object\|null`	no	—

`quickbooks_create`

Create a record.

Param	Type	Required	Default	Notes
`entity_type`	`string`	yes	—
`data`	`object`	yes	—

`quickbooks_update`

Update a record (sparse by default).

Param	Type	Required	Default	Notes
`entity_type`	`string`	yes	—
`id`	`string`	yes	—
`data`	`object`	yes	—
`sparse`	`boolean`	no	`true`	false = full replace (blanks omitted fields)
`sync_token`	`string\|null`	no	—	Omit to use the current token

`quickbooks_delete`

Delete a record (sync-token aware).

Param	Type	Required	Default
`entity_type`	`string`	yes	—
`id`	`string`	yes	—
`sync_token`	`string\|null`	no	—

`quickbooks_report`

Run a standard QBO financial report (ProfitAndLoss, BalanceSheet, AgedReceivables, …).

Param	Type	Required	Default	Notes
`report_type`	`string`	yes	—	QBO report endpoint name
`start_date`	`string\|null`	no	—	YYYY-MM-DD
`end_date`	`string\|null`	no	—	YYYY-MM-DD
`date`	`string\|null`	no	—	As-of date for point-in-time reports
`accounting_method`	`string\|null`	no	—	Cash \| Accrual
`summarize_column_by`	`string\|null`	no	—	e.g. Month, Customer

`quickbooks_export`

Export records of a type to CSV, paginated.

Param	Type	Required	Default
`entity_type`	`string`	yes	—
`filters`	`object\|null`	no	—
`max_records`	`integer`	no	`1000`

`cf_*` — Cloudflare

Zones, DNS, SSL mode, settings, cache. IMPORTANT: most cf_* tools take their args inside a nested params object (shown below as the inner fields). DNS updates are full replacements.

Curated guide: Cloudflare.

`cf_list_zones`

List all zones (id, name, status, name_servers, plan). No args.

Parameters not in the seed catalog — see the namespace reference page.

`cf_get_zone`

Look up a zone by domain name.

Param	Type	Required	Default	Notes
`params.domain`	`string`	yes	—	Exact domain, e.g. super-ht.com

`cf_list_dns_records`

List DNS records for a zone.

Param	Type	Required	Default	Notes
`params.zone_id`	`string`	yes	—
`params.record_type`	`string\|null`	no	—	A, CNAME, MX, TXT, …
`params.name`	`string\|null`	no	—	Filter by name

`cf_create_dns_record`

Create a DNS record.

Param	Type	Required	Default	Notes
`params.zone_id`	`string`	yes	—
`params.record_type`	`string`	yes	—
`params.name`	`string`	yes	—
`params.content`	`string`	yes	—
`params.ttl`	`integer`	no	`1`	1 = automatic
`params.proxied`	`boolean`	no	`false`	Orange-cloud

`cf_update_dns_record`

Replace an existing DNS record (full PUT — all fields required).

Param	Type	Required	Default
`params.zone_id`	`string`	yes	—
`params.record_id`	`string`	yes	—
`params.record_type`	`string`	yes	—
`params.name`	`string`	yes	—
`params.content`	`string`	yes	—

`cf_delete_dns_record`

Delete a DNS record (irreversible).

Param	Type	Required	Default	Notes
`params.zone_id`	`string`	yes	—
`params.record_id`	`string`	yes	—

`cf_get_ssl_mode`

Get the zone SSL/TLS mode (off|flexible|full|strict).

Param	Type	Required	Default	Notes
`params.zone_id`	`string`	yes	—

`cf_set_ssl_mode`

Set the zone SSL/TLS mode. flexible is the usual WordPress redirect-loop cause.

Param	Type	Required	Default	Notes
`params.zone_id`	`string`	yes	—
`params.mode`	`string`	yes	—	off \| flexible \| full \| strict

`cf_purge_cache`

Purge zone cache (everything or specific files).

Param	Type	Required	Default	Notes
`params.zone_id`	`string`	yes	—
`params.purge_everything`	`boolean`	no	`false`
`params.files`	`array\|null`	no	—	Specific URLs

`pve_*` — Proxmox Virtual Environment

Node/storage/template inventory, LXC & VM lifecycle, in-guest exec, async task polling. Most tools take node + vmid; lifecycle ops are async and return a task UPID.

Curated guide: Proxmox Virtual Environment.

`pve_node_status`

CPU, memory, disk, uptime, load per node. No args.

Parameters not in the seed catalog — see the namespace reference page.

`pve_lxc_list`

List LXC containers.

Param	Type	Required	Default	Notes
`node`	`string\|null`	no	—	Omit for all nodes

`pve_vm_list`

List QEMU VMs.

Param	Type	Required	Default	Notes
`node`	`string\|null`	no	—	Omit for all nodes

`pve_storage_list`

List storage pools.

Param	Type	Required	Default	Notes
`node`	`string\|null`	no	—

`pve_template_list`

List LXC templates (find the exact ostemplate before create).

Param	Type	Required	Default	Notes
`node`	`string`	yes	—
`storage`	`string`	no	`local`

`pve_lxc_create`

Create an LXC. For Docker-in-LXC set features=“nesting=1”. Returns a task UPID.

Param	Type	Required	Default	Notes
`node`	`string`	yes	—
`vmid`	`integer`	yes	—
`hostname`	`string`	yes	—
`ostemplate`	`string`	yes	—
`storage`	`string`	yes	—
`rootfs_size_gb`	`integer`	yes	—
`cores`	`integer`	yes	—
`memory_mb`	`integer`	yes	—
`features`	`string\|null`	no	—	e.g. nesting=1 for Docker
`start`	`boolean`	no	`false`

`pve_lxc_start`

Start an LXC. Returns a task UPID.

Param	Type	Required	Default	Notes
`node`	`string`	yes	—
`vmid`	`integer`	yes	—

`pve_lxc_shutdown`

Graceful shutdown of an LXC.

Param	Type	Required	Default	Notes
`node`	`string`	yes	—
`vmid`	`integer`	yes	—

`pve_lxc_stop`

Hard power-off (force required).

Param	Type	Required	Default	Notes
`node`	`string`	yes	—
`vmid`	`integer`	yes	—
`force`	`boolean`	no	`false`	Must be true

`pve_lxc_destroy`

Permanently delete an LXC (force required).

Param	Type	Required	Default	Notes
`node`	`string`	yes	—
`vmid`	`integer`	yes	—
`force`	`boolean`	no	`false`	Must be true

`pve_lxc_exec`

Run a command inside an LXC via pct exec. Returns stdout/stderr/return_code.

Param	Type	Required	Default
`node`	`string`	yes	—
`vmid`	`integer`	yes	—
`command`	`string`	yes	—

`pve_vm_exec`

Run a command inside a QEMU VM via the guest agent (needs agent: 1).

Param	Type	Required	Default
`node`	`string`	yes	—
`vmid`	`integer`	yes	—
`command`	`string`	yes	—

`pve_task_status`

Poll an async task by node + UPID.

Param	Type	Required	Default	Notes
`node`	`string`	yes	—
`upid`	`string`	yes	—

`growably_*` — Growably / LeadConnector CRM

Contacts, opportunities, conversations, tags, messaging, workflows. Discover IDs via growably_get; use growably_manage_tags (not growably_update) for tags; confirm before send_message / trigger_workflow.

Curated guide: Growably / LeadConnector CRM.

`growably_get`

Get/list by entity_type (contact, opportunity, pipeline, workflow, custom_field, conversation, …).

Param	Type	Required	Default	Notes
`entity_type`	`string`	yes	—	Selects what is returned
`id`	`string\|null`	no	—	Single record / parent id
`query`	`string\|null`	no	—	Contact search
`limit`	`integer`	no	`20`	Max 100
`start_after_id`	`string\|null`	no	—	Cursor pagination

`growably_upsert_contact`

Create or update a contact (matched by email/phone).

Param	Type	Required	Default	Notes
`first_name`	`string`	yes	—
`last_name`	`string\|null`	no	—
`email`	`string\|null`	no	—
`phone`	`string\|null`	no	—
`tags`	`array\|null`	no	—
`custom_fields`	`array\|null`	no	—	[{id, value}]

`growably_update`

Update a contact/opportunity field set. Do NOT change tags here.

Param	Type	Required	Default	Notes
`entity_type`	`string`	yes	—	contact \| opportunity
`id`	`string`	yes	—
`data`	`object`	yes	—

`growably_manage_tags`

Add/remove tags via dedicated endpoints (won’t clobber existing tags).

Param	Type	Required	Default	Notes
`contact_id`	`string`	yes	—
`action`	`string`	yes	—	add \| remove
`tags`	`array`	yes	—

`growably_add_note`

Add a note to a contact.

Param	Type	Required	Default	Notes
`contact_id`	`string`	yes	—
`body`	`string`	yes	—

`growably_create_opportunity`

Create an opportunity in a pipeline stage.

Param	Type	Required	Default	Notes
`name`	`string`	yes	—
`pipeline_id`	`string`	yes	—
`stage_id`	`string`	yes	—
`contact_id`	`string`	yes	—
`monetary_value`	`number\|null`	no	—
`status`	`string`	no	`open`	open\|won\|lost\|abandoned

`growably_send_message`

Send a message to a contact. Confirm first — cannot be recalled.

Param	Type	Required	Default	Notes
`contact_id`	`string`	yes	—
`message`	`string`	yes	—
`type`	`string`	no	`SMS`	SMS\|Email\|GMB\|WhatsApp\|IG\|FB\|Custom
`subject`	`string\|null`	no	—	Required when type=Email

`growably_trigger_workflow`

Enroll a contact in a workflow. Confirm first if it sends comms.

Param	Type	Required	Default	Notes
`contact_id`	`string`	yes	—
`workflow_id`	`string`	yes	—

`gmail_*` — Gmail (lowercase)

Search with Gmail query syntax, read, send, draft, attachments, labels. Use lowercase gmail_* (not capital-G Gmail:*). For customer-facing sends, use gmail_stage_send → gmail_confirm_send instead of sending directly.

Curated guide: Gmail (lowercase).

`gmail_search_emails`

Search using Gmail query syntax.

Param	Type	Required	Default	Notes
`query`	`string`	yes	—	e.g. from newer_than
`include_body`	`boolean`	no	`true`
`max_results`	`integer`	no	`10`

`gmail_search_emails_batch`

Search, auto-paginating until total_limit.

Param	Type	Required	Default	Notes
`query`	`string`	yes	—
`total_limit`	`integer`	no	`100`

`gmail_get_message`

Get a single message (full headers when needed).

Param	Type	Required	Default	Notes
`message_id`	`string`	yes	—
`include_body`	`boolean`	no	`true`

`gmail_send_email`

Send a message (confirm first; prefer gmail_stage_send for customer-facing).

Param	Type	Required	Default	Notes
`to`	`array`	yes	—	List of addresses
`subject`	`string`	yes	—
`body`	`string`	yes	—
`html`	`boolean`	no	`false`
`reply_to_id`	`string\|null`	no	—	Thread as a reply

`gmail_create_draft`

Create a draft for review.

Param	Type	Required	Default
`to`	`array`	yes	—
`subject`	`string`	yes	—
`body`	`string`	yes	—

`gmail_get_attachment`

Download an attachment (mind the output host).

Param	Type	Required	Default
`message_id`	`string`	yes	—
`attachment_id`	`string`	yes	—
`output_path`	`string\|null`	no	—

`gmail_stage_send`

Stage an outbound email for review. Returns send_id. Gmail API not contacted until confirmed.

Param	Type	Required	Default
`to`	`array`	yes	—
`subject`	`string`	yes	—
`body`	`string`	yes	—
`html`	`boolean`	no	`false`
`cc`	`array\|null`	no	—
`bcc`	`array\|null`	no	—
`reply_to_id`	`string\|null`	no	—

`gmail_list_staged_sends`

List pending staged email sends awaiting confirmation.

Parameters not in the seed catalog — see the namespace reference page.

`gmail_confirm_send`

Send a staged email and remove it from the staging store.

Param	Type	Required	Default	Notes
`send_id`	`string`	yes	—	From gmail_stage_send

`gmail_discard_staged_send`

Discard a staged email without sending it.

Param	Type	Required	Default	Notes
`send_id`	`string`	yes	—

`sheets_*` — Google Sheets

Read, write, and manage Google Sheets. sheets_read and sheets_write take a spreadsheet_id plus sheet/range; sheets_manage handles structural operations (add sheet, resize, format).

Curated guide: Google Sheets.

`sheets_read`

Read a range from a spreadsheet.

Param	Type	Required	Default	Notes
`spreadsheet_id`	`string`	yes	—
`range`	`string`	yes	—	A1 notation, e.g. Sheet1!A1
`value_render_option`	`string`	no	`FORMATTED_VALUE`

`sheets_write`

Write values to a range.

Param	Type	Required	Default	Notes
`spreadsheet_id`	`string`	yes	—
`range`	`string`	yes	—
`values`	`array`	yes	—	2D array of rows
`value_input_option`	`string`	no	`USER_ENTERED`	USER_ENTERED \| RAW

`sheets_manage`

Structural sheet operations: add_sheet, delete_sheet, rename_sheet, resize_sheet, batch_update.

Param	Type	Required	Default	Notes
`spreadsheet_id`	`string`	yes	—
`operation`	`string`	yes	—	add_sheet \| delete_sheet \| rename_sheet \| resize_sheet \| batch_update
`data`	`object\|null`	no	—	Operation-specific payload

`scheduler_*` — Scheduler & Job Health

Create/list/remove scheduled jobs and check whether they ran. touch_job_heartbeat is the hook external crons call at the end of every run; job_health flags anything stale.

Curated guide: Scheduler & Job Health.

`schedule_job`

Create or update a scheduled job in the Leif registry.

Param	Type	Required	Default	Notes
`name`	`string`	yes	—	Human-readable label
`command`	`string`	yes	—	Shell command; bare .py files get venv python prepended
`schedule`	`string`	yes	—	Cron expr or natural language, e.g. ‘weekdays at 8am’
`enabled`	`boolean`	no	`true`

`list_scheduled_jobs`

List all registered scheduled jobs.

Parameters not in the seed catalog — see the namespace reference page.

`remove_scheduled_job`

Remove a scheduled job by its ID.

Param	Type	Required	Default	Notes
`job_id`	`string`	yes	—

`touch_job_heartbeat`

Record that a job just ran. Call at end of any cron — including external ones (RS sync, tn_tracking_sync, etc.).

Param	Type	Required	Default	Notes
`job_id`	`string`	yes	—	Stable slug, e.g. rs-ticket-sync. Doesn’t need to be in the registry.
`exit_code`	`integer`	no	`0`	Non-zero marks job stale regardless of age
`duration_s`	`number\|null`	no	—
`note`	`string\|null`	no	—

`job_health`

Return stale/healthy/never_run buckets for all known jobs. Flags non-zero exit codes and jobs past 1.5x their cron interval.

Param	Type	Required	Default	Notes
`max_stale_minutes`	`integer`	no	`120`	Minimum stale threshold; per-job interval overrides this upward

`event_log_*` — Episodic Event Log

Append typed events for any autonomous action; query with events_since to answer what Leif did between sessions. Covers job runs, notifications, retries, webhook firings.

Curated guide: Episodic Event Log.

`log_event`

Append a typed event. Common types: job_run, notification, webhook, retry, tool_call, error, info.

Param	Type	Required	Default	Notes
`event_type`	`string`	yes	—	job_run \| notification \| webhook \| retry \| tool_call \| error \| info
`summary`	`string`	yes	—	One-line description
`details`	`object\|null`	no	—	Freeform structured payload
`source`	`string\|null`	no	—	e.g. rs-ticket-sync, tn_tracking_sync
`success`	`boolean`	no	`true`

`events_since`

Return events logged since a timestamp. Default: last 24 hours. Filter by type or success flag.

Param	Type	Required	Default	Notes
`since`	`string\|null`	no	—	ISO-8601, e.g. 2026-06-10T08:00 . Omit for last 24 h.
`event_type`	`string\|null`	no	—	Filter to one type
`limit`	`integer`	no	`200`
`success_only`	`boolean`	no	`false`

`slack_notify_*` — Slack Notifications

Send a DM to Wayne or post to a channel. Pass channel for ops-facing alerts (e.g. #ops-alerts) so Zach and Rick see them too.

Curated guide: Slack Notifications.

`send_slack_notification`

Send a Slack notification. DM to Wayne by default; pass channel to post to a channel instead.

Param	Type	Required	Default	Notes
`message`	`string`	yes	—
`priority`	`string`	no	`normal`	low \| normal \| medium \| high \| urgent
`title`	`string\|null`	no	—	Bold header above message
`channel`	`string\|null`	no	—	Channel name (#ops-alerts) or ID. Omit for DM to Wayne.

`file_transfer_*` — File Transfer & Remote Write

transfer_file does host-to-host scp with sha256 verification. remote_write_file uses base64 piping (no more 15.8 KB echo truncation). Valid dest_host values: target, shtops, runpod.

Curated guide: File Transfer & Remote Write.

`transfer_file`

Copy a local file to a remote host via scp with sha256 verification. Replaces the old chunked-b64 workaround.

Param	Type	Required	Default	Notes
`source_path`	`string`	yes	—	Absolute path on Leif (10.10.0.25)
`dest_host`	`string`	yes	—	target \| shtops \| runpod
`dest_path`	`string`	yes	—	Absolute path on dest host
`timeout`	`integer`	no	`120`

`remote_write_file`

Write a file on the target SSH host via base64 pipe + sha256 verify. No size limit; replaces echo-based approach.

Param	Type	Required	Default	Notes
`path`	`string`	yes	—
`content`	`string`	yes	—

Tools — the curated catalog overview and routing rules
Cloudflare Pages Deploys — how a regenerated page reaches production

Tool Catalog (generated)

cwa_* — ConnectWise Automate (RMM)

cwa_search

cwa_get

cwa_status

cwa_execute

cwa_run_command

cwa_run_powershell

cwa_search_scripts

cwa_script_history

cwa_raw_request

cwa_probe_command_endpoint

hudu_* — Hudu (IT Documentation)

hudu_get

hudu_search

hudu_lookup

hudu_create

hudu_update

hudu_delete

repairshopr_* — RepairShopr

repairshopr_get

repairshopr_create

repairshopr_update

repairshopr_delete

repairshopr_comment

repairshopr_search

quickbooks_* — QuickBooks Online

quickbooks_query

quickbooks_get

quickbooks_create

quickbooks_update

quickbooks_delete

quickbooks_report

quickbooks_export

cf_* — Cloudflare

cf_list_zones

cf_get_zone

cf_list_dns_records

cf_create_dns_record

cf_update_dns_record

cf_delete_dns_record

cf_get_ssl_mode

cf_set_ssl_mode

cf_purge_cache

pve_* — Proxmox Virtual Environment

pve_node_status

pve_lxc_list

pve_vm_list

pve_storage_list

pve_template_list

pve_lxc_create

pve_lxc_start

pve_lxc_shutdown

pve_lxc_stop

pve_lxc_destroy

pve_lxc_exec

pve_vm_exec

pve_task_status

growably_* — Growably / LeadConnector CRM

growably_get

growably_upsert_contact

growably_update

growably_manage_tags

growably_add_note

growably_create_opportunity

growably_send_message

growably_trigger_workflow

gmail_* — Gmail (lowercase)

gmail_search_emails

gmail_search_emails_batch

gmail_get_message

gmail_send_email

gmail_create_draft

gmail_get_attachment

gmail_stage_send

gmail_list_staged_sends

gmail_confirm_send

gmail_discard_staged_send

sheets_* — Google Sheets

sheets_read

`cwa_*` — ConnectWise Automate (RMM)

`cwa_search`

`cwa_get`

`cwa_status`

`cwa_execute`

`cwa_run_command`

`cwa_run_powershell`

`cwa_search_scripts`

`cwa_script_history`

`cwa_raw_request`

`cwa_probe_command_endpoint`

`hudu_*` — Hudu (IT Documentation)

`hudu_get`

`hudu_search`

`hudu_lookup`

`hudu_create`

`hudu_update`

`hudu_delete`

`repairshopr_*` — RepairShopr

`repairshopr_get`

`repairshopr_create`

`repairshopr_update`

`repairshopr_delete`

`repairshopr_comment`

`repairshopr_search`

`quickbooks_*` — QuickBooks Online

`quickbooks_query`

`quickbooks_get`

`quickbooks_create`

`quickbooks_update`

`quickbooks_delete`

`quickbooks_report`

`quickbooks_export`

`cf_*` — Cloudflare

`cf_list_zones`

`cf_get_zone`

`cf_list_dns_records`

`cf_create_dns_record`

`cf_update_dns_record`

`cf_delete_dns_record`

`cf_get_ssl_mode`

`cf_set_ssl_mode`

`cf_purge_cache`

`pve_*` — Proxmox Virtual Environment

`pve_node_status`

`pve_lxc_list`

`pve_vm_list`

`pve_storage_list`

`pve_template_list`

`pve_lxc_create`

`pve_lxc_start`

`pve_lxc_shutdown`

`pve_lxc_stop`

`pve_lxc_destroy`

`pve_lxc_exec`

`pve_vm_exec`

`pve_task_status`

`growably_*` — Growably / LeadConnector CRM

`growably_get`

`growably_upsert_contact`

`growably_update`

`growably_manage_tags`

`growably_add_note`

`growably_create_opportunity`

`growably_send_message`

`growably_trigger_workflow`

`gmail_*` — Gmail (lowercase)

`gmail_search_emails`

`gmail_search_emails_batch`

`gmail_get_message`

`gmail_send_email`

`gmail_create_draft`

`gmail_get_attachment`

`gmail_stage_send`

`gmail_list_staged_sends`

`gmail_confirm_send`

`gmail_discard_staged_send`

`sheets_*` — Google Sheets

`sheets_read`

`sheets_write`