com.local-mcp/local-mcp

Reports the TCC permission state (screen recording, accessibility, microphone) this app needs to capture the screen and drive other apps' UI. Call it before a capture/automation run and surface the grant hints instead of failing mid-sequence. Screen Recording / Accessibility are granted in System Settings (not a JIT dialog); the URLs open the exact pane.

Creates a PowerPoint presentation (.pptx) at `path` from an array of slides, each {title, bullets:[…]}. Requires confirm=true — called without it, returns a preview of the deck instead of writing the file. The path must be somewhere Local MCP can write; Desktop/Documents/Downloads may need a one-time Files-and-Folders grant (System Settings → Privacy & Security → Files and Folders). Returns {created, path, slides}.

Reads slide text content from a PowerPoint presentation (.pptx file).

Use this when the user wants the full content of an email that lives in the Mac's Apple Mail (message ID from list_emails/search_emails). For a Microsoft 365 message ID from m365_list_emails, use m365_read_email. Pass account= (and mailbox= if known, both from list_emails/search_emails) so the lookup targets one account instead of scanning all of them. Call sequentially, not in parallel — concurrent calls serialize behind Mail.app's JXA lock and later calls will time out. Performance: body fetch is the primary latency source (avg 20s on slow IMAP). Pass include_body=false to skip it and get metadata-only (fast). Pass max_body_chars=N to cap the body at N chars after HTML stripping (default 30000; 0=unlimited). Response includes body_fetch_ms when fetch took >2s, body_omitted=true when skipped, body_truncated_at=N when cut. When a body isn't cached on this Mac, read_email returns metadata with body_omitted=true and body_omit_reason="not_downloaded" (iCloud/IMAP optimized storage) rather than making Mail fetch it (that can be slow and tie Mail up). If the user wants it anyway, retry with force_download=true to have Mail pull the body over IMAP now and return it (waits up to ~60s). Off by default; ignored while Mail is in a cooldown.

Reads messages from an iMessage conversation by chat ID or contact name.

Reads the full content of a note by name or ID. CHECK `body_format` BEFORE WRITING THE BODY BACK. "markdown" means the note's formatting (headings, bold/italic, bullet/numbered lists, checkboxes, links, monospaced) came through as Markdown and update_note takes it back as-is — literal `*`, backticks and brackets arrive backslash-escaped so they survive the round trip. "plain_text" means the formatting could NOT be recovered and `body` is flat text: writing it back REPLACES the note's structure with flat text, so edit the note by other means (or ask the user) instead of rewriting the whole body.

Use this when the user wants to remove one of THEIR saved recipes/skills (the manifests under ~/.local/share/local-mcp/recipes). Destructive with a preview gate: the first call (without confirm) shows what would be deleted; call again with confirm=true to actually delete. Bundled starter recipes can't be deleted. To modify a recipe instead, recipe_save with the same name overwrites it (upsert).

Browses installable community SKILLS — ready-made LMCP workflows other people published (a morning brief, inbox triage, a weekly report). A user would browse them to find a ready-made workflow for a repeatable multi-app task instead of building it from scratch. Returns a list of {id, title, category, description, steps, votes}; install one with recipe_install(id).

Exports a saved SKILL (recipe) as a single portable token the user can send to someone else — paste it in a message, email, or doc. The recipient installs it with recipe_import and runs it with recipe_run. A user would export a skill to share it with a teammate (a handy brief, a report, a workflow). Returns {name, skill_token} plus the readable manifest.

Returns the full manifest of a recipe by name. recipe_not_found if unknown.

Installs a SKILL someone shared with you — pass the skill_token from their recipe_export (or a raw recipe manifest JSON). Saves it to this Mac so recipe_run can use it. Safe: importing only stores the skill; when it's later run, any state-changing step (send/write/delete) previews first and needs confirmation. If a skill with the same name already exists, the import is saved under a non-colliding name. Returns {name, imported}.

Installs a community SKILL by id (from recipe_discover) onto this Mac so recipe_run can use it. Safe: installing only stores the skill; when it's later run, any state-changing step (send/write/delete) previews first and needs confirmation. If a skill with the same name already exists, it's saved under a non-colliding name. Returns {name, installed}.

Lists the user's reusable SKILLS — saved recipes (an ordered sequence of LMCP tool calls with parameters), plus bundled ones — each runnable with recipe_run. Skills turn a repeated LMCP workflow into one reusable command. A user would list them to find an existing skill for a task rather than rebuilding it from scratch. Returns each skill's name, description, and steps.

Executes a recipe end to end: binds params, runs each step's tool in order via the registry, persists the run (see recipe_runs), and returns each step's result plus any markers_path. Recipes with state-changing steps (write/send/delete) PREVIEW first — call again with confirm:true to execute; read-only recipes run immediately. A step that errors stops the run and is reported.

Shows the history of past recipe runs and their results (recorded by recipe_run), so you can reuse, compare, or debug an automation. Pass `name` for one recipe's runs, or omit for a compact history across all recipes. Pass `run_id` (with `name`) to get that run in full detail. Newest first.

Saves a reusable SKILL — a named recipe (an ordered sequence of LMCP tool calls with parameters) — to this Mac so the user can re-run it anytime with recipe_run. A user would save one to turn a multi-step LMCP workflow they repeat (a morning brief, inbox triage, a weekly report, a data pull) into a single reusable command. Saved skills can be shared with other people via recipe_export. The manifest must have a name and a non-empty steps array. Returns {name}.

Drops a named marker into the active recording's timeline. t_ms is elapsed ms since recording start. Provide bounds (global points, top-left) to zoom toward an element, or omit for full-frame. note becomes a caption source. Returns no_active_session if nothing is recording.

Renames an existing Apple Reminders list. Pass the current list name (or list_id from get_reminder_folders) and new_name. Requires confirm=true.

Use this when the user wants to reply to an email that lives in the Mac's Apple Mail (message ID from list_emails/search_emails). Supports plain text or HTML body and previews before sending. To leave the reply in Drafts WITHOUT sending, pass `save_as_draft: true`: it builds the same native Mail reply (automatic quote of the original, correct thread, Reply/Reply-All recipients) and saves it instead of sending — `send` is never called on that path. `create_draft` with `reply_to_message_id` also leaves a draft, but composes it from scratch, so it has no automatic quote. For a Microsoft 365 message ID from m365_list_emails, use m365_reply_email. Pass `account` (from list_emails/search_emails results) to skip scanning other accounts and avoid timeouts on multi-account Macs.

Send an ANONYMOUS, content-free signal when an LMCP tool fails, returns nothing useful, the user seems frustrated, or you could not accomplish what they asked. Helps the LMCP team find and fix the roughest spots. Send ONLY the category + the tool name — NEVER the user's request, message/email content, account names, or any personal data. No confirmation needed: this is anonymous (categories only) and respects the user's opt-out.

Sends a problem report, feature request, or integration request to the LMCP team — for when a user wants to report a bug, ask for a new capability, or request support for an app LMCP doesn't cover yet. Without confirm=true it returns a preview of the anonymous payload that would be sent (version, OS, permission status, and recent tool names / error-type codes — never arguments, messages or personal data); with confirm=true it submits and returns a case_id. type='problem' (default) reports a bug, type='feature' requests a new capability, type='integration' requests an unsupported app.

Submits a feature request to the LMCP team — a new capability, a tool that doesn't exist yet, or an app/integration the user wishes LMCP supported. A user would invoke this when they want to ask the team for something LMCP can't do yet. Without confirm=true it returns a preview; with confirm=true it submits. The request includes the machine ID and (if set) the account email so the team can follow up — it is not anonymous.

Runs a fast health check of all LMCP integrations on this machine, including the AI apps connected to LMCP (configured, never used, broken command, blocked config). Shows what works, what doesn't, and how to fix it. Optionally submits a report to the LMCP team.

Saves an attachment from an email to disk. Requires confirm=true; without it you get a preview of where the file would be written. Pass account= (and mailbox= if known, both from list_emails/search_emails) so the lookup targets one account instead of scanning all of them.

Begins a screen recording (ScreenCaptureKit) of a display, window, or region. Single active session in v1 — a second start returns already_recording. Returns a session_id used by record_marker and screen_record_stop. Requires Screen Recording permission; without it returns an explicit permission_required error, never a silent no-op.

Reports whether a recording is active, with the session_id, elapsed_ms, output path, and marker_count.

Stops the active recording, finalizes the .mov, and writes the marker timeline JSON (§6) next to it. Returns the video path, duration, resolution, marker_count and markers_path. Returns no_active_session if nothing is recording.

Captures a single frame of a display, window, or region to a PNG. Returns {path, resolution (PIXELS), scale_factor, display_id} — scale_factor is the backing scale of the display that was ACTUALLY captured (the same value list_displays reports for that display_id, by construction: both read one function), so pixels = points x scale_factor when converting a coordinate from the image to ui_click. If the display could not be determined you get scale_factor_unknown instead of a guess; resolution is always there, so you can derive the ratio yourself. Requires Screen Recording permission; without it returns an explicit permission_required, never a blank image.

Searches the Mac's Contacts app (Contacts.app, local/iCloud) by name, email, or phone number. For a Microsoft 365 directory use m365_search_contacts or search_m365_directory instead.

Use this when the user wants to find specific emails on this Mac (Apple Mail — any account added to Mail.app). Searches subject and sender by default; pass scope="body" or scope="all" to also search the message body (see search_coverage in the response — a body search can be partial while its local index is still building). For a Microsoft 365 mailbox NOT added to Mail.app, use m365_search_emails. IMPORTANT: on machines with 2+ accounts, call with account=<name> (from list_email_accounts). Without it, and when the fast index can't answer, search_emails returns the account list instead of scanning all of them — scanning every account in one call has no time limit and can block Mail for other requests too. Exactly 1 account is unaffected.

Search your organization's Microsoft 365 directory for users by name or email. Returns matching users with their title, department, and contact info.

Searches iMessage conversations by content, sender name, or date range.

Searches Apple Notes by title or content. Paginated: `limit` is capped at 100 per call, so page with `offset` instead of asking for a bigger limit. The response carries `total` (how many notes match the query in all) and `has_more`, so a capped page is never mistaken for the complete answer — page until `has_more` is false, which is exact even when `total_is_estimated` says the count is only a lower bound. To walk every match, pass order="id" — see the order parameter.

Searches OmniFocus tasks by name or note content.

Use this when the user wants to send an email from an account configured in the Mac's Apple Mail. Composes and sends via Mail.app; supports plain text or HTML body. For sending from a Microsoft 365 account NOT added to Mail.app, use m365_send_email. Pass `from` to send from a specific configured Mail.app account instead of the default sender. Pass `attachments` as a comma-separated list of absolute file paths to attach files.

Sends an iMessage via the Mac's Messages.app to a recipient handle (phone number with country code, e.g. +14155551234, or an Apple ID email). This is a write operation: the first call (without confirm) returns a preview; call again with confirm=true to actually send. Direct (1:1) iMessage only — sending into an existing group chat isn't supported yet. Requires Messages.app signed in to iMessage + Automation permission.

Returns a personalized LMCP install link and setup steps (~30 sec to install). LMCP is a free Mac and Windows app that gives access to Mail/Calendar/Contacts/Notes/Reminders on Mac, Outlook/Teams/OneDrive/Office on Windows, and 100+ tools on the user's machine (data stays local). A user would invoke this to install LMCP or reconnect it. Pass os ("macos" or "windows" for real install steps; linux/ios/android go to a waitlist). Optional: email, step, issue.

Composes a Signal message and returns step-by-step guidance for the user to send it themselves. This tool does NOT send: Signal Desktop exposes no local send API and LMCP reads its database read-only, so it cannot transmit Signal messages. Call it when the user wants to message someone on Signal — it drafts the text and tells them how to deliver it. First call (show_send_steps=false or omitted) returns a preview; show_send_steps=true returns the send-it-yourself steps. chat_id should come from a previous signal_list_chats call — never fabricate IDs.

Connect Signal to Local MCP. Reports whether Signal Desktop is installed and signed in, and tells you exactly what to do next — install Signal, or open it and link your phone. (Signal links inside its own desktop app, so the QR is shown there, not here.) Once you're signed in, signal_list_chats / signal_read_messages work. If Signal is already connected, it just reports that.

Lists Signal conversations (chats) with last-active timestamps. Reads from the local Signal Desktop database — no network access required. Returns chat IDs, contact names, and type (direct or group). Use the chat_id in subsequent signal_read_messages calls.

Reads messages from a specific Signal chat. The chat_id must come from a previous signal_list_chats call. Returns messages in chronological order with sender phone numbers and body text. Only messages cached locally by Signal Desktop are available.

Full-text search across locally-cached Signal messages. Only messages Signal Desktop has stored on disk are searched — no network access required. Optionally restrict search to a specific chat_id.

Lists channels in a Slack workspace, including public channels, private channels, and direct messages (DMs). Reads from the local IndexedDB cache — only channels that Slack Desktop has synced to disk are returned. Pass workspace_id from slack_list_workspaces to filter to a specific workspace.

Lists the Slack workspaces (teams) the user has connected in Slack Desktop. Start here for Slack — the workspace id it returns is what slack_list_channels / slack_read_channel_messages / slack_search_messages need. Reads from the local IndexedDB cache — no token needed. Only workspaces that have been synced to disk are returned.

Reads recent messages from a Slack channel or DM. Reads from the local IndexedDB cache — only messages that Slack Desktop has synced to disk are available (typically the last few hundred messages for active channels). channel_id must come from slack_list_channels.

Searches Slack messages. Optionally restrict to a specific channel_id. A hit whose `text` is the marker "[body not included in this search result]" (with `body_missing: true`) DID match — its body was lost by the reader, not empty. Read it with slack_read_channel_messages on its channel_id; never report it to the user as an empty message. Direct messages come back as an unresolved id rather than a name; slack_list_channels maps ids to names.

Gets historical price data for a stock symbol. Range: 1d, 5d, 1mo, 3mo, 6mo, 1y, 2y, 5y, 10y, ytd, max.

Gets current stock price and market data for one or more symbols (e.g. AAPL, MSFT, BTC-USD). Uses Yahoo Finance — no API key required.

Searches for a stock ticker symbol by company name (e.g. "Apple" → AAPL). Start here for Stocks — the symbol it returns is what stocks_get_quote / stocks_get_chart need.

Shows or submits the short in-product survey Local MCP assigned to this machine. Called with NO arguments it returns the pending survey and, in clients that support MCP Apps, renders it as an interactive card the user answers directly — prefer this. To submit conversational answers instead, pass `answers` keyed by each question's `id` (single/scale = one value, multiple = an array of values): call once to PREVIEW, then again with confirm=true to record. Do NOT invent answers — if no human gave them (you're running autonomously), call survey_skip instead.