"Using voice commands to interact with Claude on desktop" matching MCP tools:

• submit_video_jobA

  Autosophia Agent VideoA

  Turn a script into a finished 1080p video — narrated, cut to matched stock footage, subtitles burned in, audio normalized to −14 LUFS. Returns a job id; poll get_job, then fetch_video. Use when you need a publishable video and have only text. $0.60 per video in USDC on Solana — no account, no API key, no human in the loop. script: narration body to speak (plain text) title: optional intro title shown for ~4s at the top voice: voice id from list_voices(), e.g. female_warm subtitles: burn-in subtitles (default true) speed: narration speed multiplier, e.g. 1.0 seed: stock-selection seed for reproducible visuals, e.g. 7

  ConnectorNo auth

• text_to_speechA

  Ciro Cesar Maciel — Free ToolsA

  Reads a text aloud in a natural Portuguese voice from Fish Audio — Rafael by default, or one of six others — and returns an MP3. WHEN TO USE: the user wants to hear a Portuguese text or needs an audio file of it — narration, audiobook, lesson, voice-over, a message read aloud. The voices speak Portuguese (Brazil, and Tomás from Portugal); a text in another language is read with their accent. HOW IT WORKS: - Up to 50,000 characters per call. A text over 1,000 characters is split by sentence into parts of up to 1,000; the parts are voiced three at a time and joined in order into ONE MP3. Progress is reported per part ("Gerando áudio... 3 de 18"), so keep waiting while it arrives. - It takes time: about 25 seconds per round of three parts. 1,000 characters ≈ 25 s; 5,000 ≈ 1 min; 16,000 ≈ 2.5 min; 50,000 ≈ 7 min. - Over 50,000 characters: split the text at paragraph boundaries into several calls with the same voice and speed, and give the user every link, in order. - Send the text as it should be HEARD: remove Markdown marks (**, #, list bullets), URLs, emojis and tables. Do not summarize, translate or reword unless the user asked — every word you send is read. - voice: rafael (default) or beatriz for clear, neutral narration; tomas for European Portuguese; narrador-propagandas for ads; rodolfo, sao-cipriano and capitao-nascimento are deep character voices. - speed: 1 is the voice's natural pace; 0.9 suits calm narration, 1.2 a quick read. RETURNS: - audioUrl: the complete MP3 to download, valid for 7 days. Always give this link to the user. If you can run commands, you can download it (e.g. curl -o audio.mp3 <audioUrl>). - audio: the MP3 itself, only when it is short (about a minute or less); otherwise null. - seconds (duration), parts, characters, voice, speed. - link: this tool's web page with the same voice and speed (the text is not in it). ERRORS say what happened and what to do next. If a part fails, no audio is produced and a new call starts again from part 1.

  ConnectorNo auth

• well_delete_claude_code_sessionA

  WellA

  Remove one stopped Claude Code session from the person's list of sessions. Use it when the person asks to remove a session from the list. Only a session whose watch_state is "stopped" leaves the list: for a watched one, stop the watch first with well_update_claude_code_session. It does not close the tab and does not stop the session on claude.ai. Find the id first with well_list_claude_code_sessions. REQUIRED: claude_code_session_id. Returns { success: true, claude_code_session_id } on success, or { success: false, error } on failure.

  Connector

  Destructive

  No auth

• download_mediaA

  WA MCPA

  Fetches a photo, sticker, voice note, audio, video or document from a WhatsApp message, only when the user asks for it. Paid plan only: on the free plan the call is refused with a note on how to subscribe. Small images are returned as an image you can look at. Everything else returns a download link valid for 15 minutes: share it with the user. You cannot play or transcribe audio yourself. Get message ids from search_messages (media appears as e.g. "[voice note, 0:42]") or read_chat_history.

  ConnectorOAuth

• receptionist_call_voiceA

  LatchbellB

  Owners only (needs sign-in): Sets the speech model voice for this business's phone line (inbound and every place_phone_call), until changed again. Default is Aoede. Pass a Gemini prebuilt voice name (letters only, e.g. "Aoede", "Puck"); pass an empty string to reset to the default. place_phone_call cannot pick a different voice per call — set it here or read phone.call_voice in receptionist_service. Tone and language on a specific outbound call belong in place_phone_call's purpose; the inbound opening line belongs in front_desk greeting (update_front_desk).

  ConnectorNo auth

• input.click_xyA

  GlasswarpA

  Click at native screen coordinates (0…native_width-1, 0…native_height-1 from screen.observe). Last resort when no suitable UIA target exists — prefer input.click_target. Never use JPEG/downscaled pixel coords. Side effect: real mouse click on the remote desktop.

  Connector

  Destructive

  No auth

• upload_fileA

  CluesoA

  Upload files to Clueso. Pick a mode by client and where the file lives: - `files` (ChatGPT only): the user's attachments, filled by ChatGPT; pass them instead of asking for a re-upload. - `file_name` (default for agents/scripts: Claude Code, Cursor, Claude Desktop): returns an upload URL on Clueso's own domain (not S3; works where cloud storage is blocked) + a ready curl that PUTs one local file; you or the user run it. - `file_names` (without request_hosted_upload): the same for many files, one token + URL each and ONE curl for all; run it from the folder the names are relative to (edit_animation upload_ids: the page site's root, e.g. 'index.html', 'js/scene.js'). - `file_url`: a public https URL; the server fetches it; mcp_upload_id returned at once. - `request_hosted_upload` (only when a human should pick files in a browser, or no shell/PUT): one upload_token + upload_page link covering every file dropped; the user drops files and clicks Done; then check_uploads(upload_token). Call once for all files. The mcp_upload_id (`mup_…`) goes to: - add_elements / update_elements: an image/video ON a clip (or a source swap) as `type_data.mcp_upload_id`; an animation's image slot inside `type_data.parameter_values` on update_elements only (stripped on add). - add_audio (project music track) · add_clips(kind='video') (video/audio → clip with transcription) · add_clips(kind='pptx') · add_article_media · analyze_audio · edit_animation (`files: [{path, upload_id}]` or `upload_ids` named by path, so big files never go inline). purpose: 'font' (any mode; display_name optional) adds it to this workspace's brand fonts once it arrives: the curl's reply (this reply for file_url/files, check_uploads for the hosted page) carries `font: {name, family, format, converted_from}` or `font_error`. TTF, OTF, WOFF, WOFF2 (WOFF/WOFF2 stored as TTF). Name = display_name, else the family without build dates/versions ("Cursor Mono 260406" → "Cursor Mono"); use it exactly in font_setting.font and pages. One face per name; an existing name is refused. Needs editor/admin and a plan with custom fonts.

  ConnectorNo auth

• set_voiceA

  CluesoA

  Set the voiceover voice for every clip in a project, or only for the clips in `clip_ids`. Use this to apply a clueprint's voice (read `voiceover.voice.name` and `voiceover.voice.engine` from the clueprint source data), or to switch all clips to a specific voice in one call. When the user names specific clips, pass their ids in `clip_ids` so the other clips keep their voice. The voice is looked up by name (case-insensitive; a saved voice's code also works), preferring `voice_engine`. Never guess a name: a name that matches nothing applies the workspace default and returns `matched: false` with a note. Then pick a real voice with find(type='voices'), re-apply, and tell the user. `engine_substituted: true` means the named voice exists only on another engine and was applied there. Common engines: 'eleven' (ElevenLabs), 'cartesia', 'google'. ElevenLabs voices use the latest voice generation unless `voice_version` says otherwise; a voice the workspace saved keeps its saved version. Leave it unset; pass "legacy" ONLY when the user explicitly asks for the legacy/older voice generation.

  ConnectorNo auth

• check_signupA

  UseroA

  Poll after start_signup. Returns { status: "pending" } until the user presses the button in the email, then { status: "ready", apiKey, setup } exactly once; the pollToken is dead after that. The setup field holds the exact config or command for this client plus what to tell the user (restart, or remove-and-re-add on Desktop). Poll every 5 seconds for up to 15 minutes without ending your turn. On ready, apply the setup snippet at once, then call create_client for the product.

  ConnectorNo auth

• validate_pythonA

  CodeCraftA

  Validates a Python automation script that runs OUTSIDE the game, on three axes: Python syntax (using the real interpreter), Minecraft commands embedded in the script (against the official command index), and the shape of the /connect WebSocket message envelope. For behavior pack scripts use validate_script instead — Python does not run inside a pack. The embedded command check is the most valuable one: a command written from memory can look syntactically fine and still do nothing in the game. Only strings starting with / are treated as commands. If syntax could not be checked, syntaxChecked is false in the result; ok:true alone does not mean the syntax is valid.

  ConnectorNo auth

• create_characterA

  VidGuyA

  Create a new saved character/actor for UGC video — the API equivalent of adding an actor in the dashboard. Supply ONE of: fromLibraryId (clone a preset from list_character_library into the user's saved actors — FREE, name/voice default to the preset's); imageUrl (a public/hosted image — use import_asset_from_url or create_upload first if you only have raw bytes — saved for FREE); or a text prompt to AI-generate a 9:16 portrait (SPENDS 1 credit). Returns characterId to pass as the UGC characterId on create_video. Optionally set defaultVoiceId. NOTE: a library preset can already be used directly as a UGC characterId — only clone it here when the user wants their own editable copy (e.g. a custom voice).

  Connector

  Destructive

  OAuth

• tegas_edit_videoA

  Tegas AIA

  Paid: each re-voiced scene costs tokens like a normal generation (about 10 T per scene voice-over); scene clip, subtitle, music and volume changes alone are not charged; a failed edit is refunded. Edit a finished video in place and rebuild it: this REPLACES the whole video end to end and typically takes a few minutes, the same as the original render - it is not a quick patch. Tell the user what you are about to change before calling this, then poll with tegas_wait_video (or tegas_video_status) after the call; do not call this again for the same video until the rebuild finishes. Pass at least one of the groups below; omit a group entirely to leave it untouched: - scenes: list of {"index": int, "voiceover_text"?: str, "subtitles_text"?: str, "video_url"?: str} - one entry per scene to change, each needs at least one of the three fields. - voice: {"id"?: str, "gender"?: "female"|"male", "language"?: "ru"|"en"|"es"|"fr"|"de"|"tr"} - changing any of id/gender/language RE-VOICES EVERY SCENE that has voice-over text, not just the ones listed in `scenes`. - subtitles: {"enabled"?: bool, "style"?: "tiktok"|"phrases"|"contrast", "appearance"?: {"alignment"?, "font_size"?, "font_family"?, "text_color"? (hex "#RRGGBB"), "color_saturation"?}} - you cannot disable subtitles and set their style/appearance in the same call, that fails with 422 validation_error; disable them in one call and restyle in a later one. - music: {"enabled"?: bool, "url"?: str} - url must come from tegas_upload_music (or another public https URL). - volumes: {"voice"?: int, "music"?: int, "master"?: int} - each 0..100. - watermark: bool - the Tegas watermark on the finished video. Must be the ONLY change in the call, not combined with scenes/voice/subtitles/music/volumes: the renderer rebuilds the watermark through a separate step, so mixing it with other changes fails with 422 validation_error. Change the watermark in its own call. Returns video_id, status "processing" and edits_accepted - the list of groups that were actually applied (e.g. ["voice", "subtitles"], or ["watermark"] for a watermark-only edit). If the video is still rendering or being rebuilt from a previous edit, this fails with 409 video_busy or edit_in_progress (the edit was NOT accepted) - wait for status completed (tegas_wait_video) and try again, do not retry immediately in a loop.

  Connector

  Destructive

  OAuth

• safe_preflight_checkA

  AgentWorldB

  [PAID $0.01 USDC per call — optional third-party check] Preflight a proposed command or tool call through HumanMirror Safe Preflight (humanmirror.fr, x402-verified seller) before executing it. Returns the independent risk verdict (risk level, findings, required guards) from their circuit engine. Use for genuinely risky external tool calls where a second opinion matters. Benign commands settle $0.01 USDC on Base and return the verdict; commands they judge over-limit are blocked and refunded (no charge). This is an OPTIONAL external check — AgentWorld's own spend-authority, solvency and circuit-breaker layers remain primary and free.

  ConnectorNo auth

• propose_review_replyA

  ShearQuery — Barber & Beauty Industry DataA

  Draft a public reply to one review, using its id from my_reviews. Replaces any existing reply. Two or three sentences in the owner's voice; never offer discounts, argue, or share personal details. Creates a DRAFT only — nothing on Google changes. Show the owner the draft this returns, word for word, and publish it with publish_change only after they say yes.

  ConnectorNo auth

• cast_enhance_voiceA

  Mubert Cast MCPA

  AI cleanup of a recording: `speech` = noise + room removal (strength subtle/medium/strong), `music` = keep only the voice from a mixed track, `bg_music` = voice + a little of the original bed. Free. Produces a NEW audio_file_id — use it as the voice source in cast_build_project (cuts planned on the original still apply: same timeline). Enhance the ORIGINAL upload, not an already-enhanced file. On the free plan an API call returns a 60-second head preview (enough to A/B it) — the full-length render is one free click in the editor, or a paid-plan API call. The response says which you got.

  ConnectorOAuth

• preview_agent_launchA

  AgentOnAirA

  Preview what AgentOnAir onboarding would give an agent: its show name, page and RSS feed, a first-episode title and script template, and next steps. Use it before registering; pick the voice with list_voices. Always a dry run: it creates nothing, reserves no name and returns no API key. Registering for real is POST /v1/quick-start on the REST API.

  ConnectorNo auth

• safe_preflight_checkA

  AgentWorld — Live AI Agent EconomyB

  [PAID $0.01 USDC per call — optional third-party check] Preflight a proposed command or tool call through HumanMirror Safe Preflight (humanmirror.fr, x402-verified seller) before executing it. Returns the independent risk verdict (risk level, findings, required guards) from their circuit engine. Use for genuinely risky external tool calls where a second opinion matters. Benign commands settle $0.01 USDC on Base and return the verdict; commands they judge over-limit are blocked and refunded (no charge). This is an OPTIONAL external check — AgentWorld's own spend-authority, solvency and circuit-breaker layers remain primary and free.

  ConnectorNo auth

• lab_dub_voicesA

  FilmLabA

  List the ElevenLabs TTS voices available for lab_dub_tts's `voice_id` — this is the EN-dub-track text-to-speech voice list, NOT a project's cloned voices (those are lab_list_voices). Reads only — no state changes, no credits. If ELEVENLABS_API_KEY isn't configured on the backend the list comes back empty and `configured` is false.

  ConnectorOAuth

• delete_migration_redirectsA

  SEO GSC Wizard MCPA

  Permanently deletes saved redirect mappings. Narrow the deletion with `label` and/or the A/B property pair; to delete EVERY mapping on the account you must pass confirmDeleteAll: true, since an unnarrowed delete would also wipe unrelated migrations. Preview exactly what would go with list_migration_redirects using the same filters first.

  Connector

  Destructive

  OAuth

• create_voice_cloneA

  UnsoraB

  Create an instant voice clone from a speech recording (ElevenLabs). Only clone the user's own voice or a voice they have permission to use. Best results: 1–2 minutes of clean speech with no music or background noise. Costs 15 credits; max 10 clones per account. Returns clone.id — use it as voice_id in create_voiceover, create_avatar_video and change_voice. In app-capable hosts the result renders as an interactive panel the user can see and act on — do NOT repeat its contents as a list or table in your reply; add only what the panel doesn't say.

  ConnectorOAuth

• get_setup_kitA

  NEXUS AGIA

  Return the optional setup kit for agents that run on the user's own machine (Claude Code, Cursor). The kit contains four hooks (recall at session start, recall on each prompt, sync of session recaps, and the inbox of messages from other agents), the settings.json block, a usage policy, and an idempotent bash script that installs them. With the hooks installed, memory is recalled and stored automatically. Without them, NEXUS only has what the agent stores through its tools. Calling this tool only returns the kit; nothing is installed until the script is run. Running it writes the hooks and the policy file on the user's machine, declares the hooks in the client's settings, and loads the policy into the agent's instructions (a line in CLAUDE.md for Claude Code, a .cursor/rules file for Cursor), so installing is the user's decision. It does not apply to chat clients (Claude web or desktop, ChatGPT). Side effect: on an OAuth connection, the call issues the hooks credential and embeds it in the script. This works once, because a secret that was already shown is not returned again. On a plain `nxa_` token connection it does not issue a credential, and an account owner must issue one. `steps` says which case applies. Args: formato: "script" (default) for the bash installer plus steps, or "files" for the same files as text, for clients without bash. It is ignored for Cursor. client: "claude-code" (default) or "cursor". Cursor gets a session-start hook and a turn-recap hook. It has no per-prompt recall, because Cursor's beforeSubmitPrompt cannot inject context.

  ConnectorAPI key