Official Speak AI MCP Server — capture meetings, search thousands of recordings, run async voice and video surveys, create clips, and automate
Official Speak AI MCP Server — capture meetings, search thousands of recordings, run async voice and video surveys, create clips, and automate workflows from your
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| update_transcription | Edit the official transcript text of a media file by finding and replacing text |
| get_signed_upload_url | Get a pre-signed S3 URL for direct file upload |
| upload_media | Import an audio or video file from a direct public URL, a get_signed_upload_url URL, or a supported page link (YouTube, TikTok, Instagram, X/Twitter, Facebook, |
| upload_local_file | Upload a local file directly from disk (stdio and CLI only, never on the remote server) |
| upload_and_analyze | Upload media from a URL (direct file, or any social/video page link upload_media accepts — resolved automatically) and return its media_id immediately. Poll get |
| list_media | List and search media files with filters, pagination, and optional inline data (transcripts, speakers, keywords) via include param |
| get_media_insights | Get AI insights — topics, sentiment, summaries, action items |
| get_transcript | Get full transcript with speaker labels and timestamps |
| get_captions | Get subtitle-formatted captions for a media file |
| update_transcript_speakers | Rename speaker labels in a transcript |
| bulk_update_transcript_speakers | Rename speaker labels across multiple media files in one call (max 500) |
| get_media_status | Check processing status (pending → processed) |
| update_media_metadata | Update name, description, tags, or folder |
| delete_media | Permanently delete a media file |
| toggle_media_favorite | Mark or unmark media as a favorite |
| reanalyze_media | Re-run AI analysis with latest models |
| bulk_move_media | Move multiple media files to a folder in one call |
| upload_and_analyze_batch | Upload up to 25 URLs in one call, 5 at a time. Each URL is reported as uploaded or failed with its reason, so one bad link does not sink the batch. |
| ask_ai_chat | Ask AI questions about media, folders, or your whole workspace |
| retry_ai_chat | Retry a failed or incomplete AI Chat response |
| get_chat_history | List recent AI Chat conversations |
| get_chat_messages | Get full message history for conversations |
| delete_chat_conversation | Delete a whole chat conversation and its messages |
| list_prompts | List recent AI chat messages with their answers and sources |
| get_favorite_prompts | Get all favorited prompts and answers |
| toggle_prompt_favorite | Mark or unmark a chat message as favorite |
| update_chat_title | Rename a chat conversation |
| submit_chat_feedback | Rate a chat response (thumbs up/down) |
| get_chat_statistics | Get AI Chat usage statistics |
| export_chat_answer | Export a conversation or answer |
| get_analysis_quote | Check if a file can be analysed as audio/video and what it costs |
| search_media | Deep search across transcripts, insights, and metadata with filters |
| get_media_statistics | Get workspace-level stats — counts, storage, processing breakdown |
| list_supported_languages | List all supported transcription languages |
| list_folders | List all folders with pagination and sorting |
| get_folder_info | Get folder details and contents |
| create_folder | Create a new folder |
| clone_folder | Duplicate a folder and its contents |
| update_folder | Rename or update a folder |
| delete_folder | Delete a folder (media is preserved) |
| get_all_folder_views | List all saved views across folders |
| get_folder_views | List views for a specific folder |
| create_folder_view | Create a saved view with custom filters |
| update_folder_view | Update a saved view |
| clone_folder_view | Duplicate a view |
| create_recorder | Create a new recorder or survey |
| list_recorders | List all recorders |
| get_recorder_info | Get recorder details and questions |
| clone_recorder | Duplicate a recorder |
| get_recorder_recordings | List all submissions |
| generate_recorder_url | Get a shareable public URL |
| update_recorder_settings | Update branding and permissions |
| update_recorder_questions | Update survey questions |
| check_recorder_status | Check if recorder is active |
| delete_recorder | Delete a recorder |
| create_clip | Create a highlight clip from time ranges across media files |
| get_clips | List clips or get a specific clip with download URL |
| update_clip | Update clip title, description, or tags |
| delete_clip | Permanently delete a clip |
| export_media | Export as PDF, DOCX, SRT, VTT, TXT, or CSV |
| export_multiple_media | Batch export with optional merge into one file |
| list_meeting_events | List scheduled and completed events |
| schedule_meeting_event | Schedule AI assistant to join a meeting |
| remove_assistant_from_meeting | Remove assistant from active meeting |
| delete_scheduled_assistant | Cancel a scheduled meeting assistant |
| get_live_meeting_transcript | Pull only the new sentences added to a live (or just-ended) meeting transcript since your previous call. Works on Zoom / Google Meet / MS Teams while the bot is |
| list_automations | List automation rules with paging and filters |
| get_automation | Get automation details (trigger + step graph) |
| create_automation | Create an automation rule (V2 trigger + steps graph) |
| update_automation | Update an automation (replaces trigger + steps) |
| toggle_automation_status | Enable or disable an automation |
| list_automation_names | List names and ids of active automations that have an AI chat step |
| get_automation_runs | Get an automation's run history |
| bulk_update_automation_status | Activate/deactivate multiple automations |
| bulk_assign_automation_folders | Set folder scope for multiple automations |
| run_automations | Manually run automations against media now |
| delete_automation | Permanently delete an automation |
| list_automation_apps | List catalog apps: Speak built-ins plus third-party apps marked connected or not connected (read-only) |
| list_automation_triggers | List catalog trigger types (optionally by app) |
| list_automation_actions | List catalog action/step types (optionally by app) |
| build_automation | Create or update an automation from a friendly spec, without the wire format |
| get_automation_run | Get one run in full — every step, plus which way each branch went |
| get_automation_run_stats | Aggregate run outcome counts over a period |
| test_automation | Run an automation once against one media item (real side effects) |
| validate_automation_graph | Check a step graph for problems without saving it |
| describe_automation_graph | Show a saved automation's steps as an indented branch tree |
| create_webhook | Create a webhook for event notifications |
| list_webhooks | List all webhooks |
| update_webhook | Update a webhook |
| delete_webhook | Delete a webhook |
| provision_inbound_webhook | Provision a standalone inbound webhook and get its public receive URL |
| get_inbound_webhook | Get an inbound webhook's receive URL, sample payload, and trigger tokens |
| get_webhook_attempts | Get the delivery log for an inbound webhook, with acknowledgement status |
| create_text_note | Create a text note for AI analysis (uses the plan allowance, then credits) |
| get_text_insight | Get AI insights for a text note |
| reanalyze_text | Re-run AI analysis on a text note |
| update_text_note | Update a note's name or content (only a note not yet analyzed is analyzed) |
| list_fields | List all custom fields |
| create_field | Create a custom field |
| update_field | Update a custom field |
| update_multiple_fields | Batch update multiple fields |
| list_labels | List workspace labels and groups as a tree |
| create_label | Create a label or a label group |
| update_label | Rename, recolor, describe, move or reorder a label |
| archive_label | Archive a label (a group takes its labels along) |
| restore_label | Restore an archived label or group |
| merge_labels | Move every use of one label onto another |
| add_speak_label_sets | Add ready-made Speak label groups |
| list_media_labels | List the labels applied to a transcript |
| apply_label | Label transcript words, found by quote or word range |
| update_media_label | Change a span's labels, confirm it, or move it |
| remove_media_label | Remove a labelled span |
| list_media_comments | List a file's comment threads |
| add_comment | Comment on the file or on words, or reply to a thread |
| update_comment | Edit the text of your own comment |
| resolve_comment | Resolve or reopen a thread |
| delete_comment | Delete a comment |
| create_embed | Create an embeddable player widget |
| update_embed | Update embed settings |
| check_embed | Check if embed exists for media |
| get_embed_iframe_url | Get iframe URL for your website |
| list_users | List workspace members with ids, emails, and permissions |
| list_user_groups | List user groups with hydrated members |
| create_user_group | Create a user group and assign members |
| update_user_group | Update a group's name and members (full replace) |
| delete_user_group | Delete a user group |
| list_dashboard_widgets | List widget types, their config keys, and an example payload |
| list_dashboards | List analytics dashboards you can access |
| get_dashboard | Get a dashboard's full config (widgets, filters, scope) |
| create_dashboard | Create a dashboard with auto-laid-out widgets |
| update_dashboard | Update a dashboard (partial; widgets are replaced) |
| delete_dashboard | Soft-delete a dashboard and its share link |
| duplicate_dashboard | Clone a dashboard with fresh widget ids |
| share_dashboard | Enable public sharing and return the share token |
| get_dashboard_speakers_insight | Speakers breakdown for a folder/date/filter scope |
| list_voice_agents | List the company's voice agents (newest first) with their config |
| get_voice_agent | Get a single voice agent by agentId |
| create_voice_agent | Create a voice agent (name, personality, instructions, and voice are required) |
| update_voice_agent | Update a voice agent; send only the fields you want to change |
| delete_voice_agent | Delete a voice agent; its share link, questions, and test suite stop working (no restore tool) |
| create_voice_agent_from_prompt | Create a new agent from a plain-English description; an LLM generates its name, instructions, and settings |
| generate_voice_agent_config | Run the same prompt-to-config generation against an existing agent |
| get_voice_agent_setup_guide | Discovery helper: the build order, which tool covers each piece, common mistakes |
| list_voice_avatars | List the video avatars available to attach to a voice agent |
| list_voices | List the text-to-speech voices available to a voice agent |
| list_voice_conversations | List conversations handled by voice agents (filter by agentId) |
| get_voice_conversation | Get a single conversation by conversationId |
| list_voice_questions | List the questions configured on a voice agent, in ask order |
| get_voice_question | Get a single question by fieldId |
| create_voice_question | Attach a question template to a voice agent |
| update_voice_question | Partially update a voice agent question |
| delete_voice_question | Remove a question from a voice agent |
| reorder_voice_questions | Set the order a voice agent asks its questions in |
| list_voice_question_templates | List the shared and company-owned question template library |
| create_voice_question_template | Create a company-scoped custom question template |
| get_voice_test_suite | Get a voice agent's test suite (its scenarios and run settings) |
| update_voice_test_suite | Create or update a voice agent's test suite (upserts; replaces scenarios) |
| generate_voice_test_suite | Auto-generate a default test suite from the agent's name, personality and instructions |
| start_voice_test_run | Queue a test run of a voice agent's scripted test suite (creates a queued run record; no calls are placed) |
| get_active_voice_test_run | Get a voice agent's currently active run (queued, running, or paused) |
| pause_voice_test_run | Pause a running or queued test run |
| resume_voice_test_run | Resume a paused test run |
| cancel_voice_test_run | Cancel a test run; terminal, cannot be resumed |
| list_voice_test_runs | List a voice agent's test runs, most recent first |
| get_voice_test_run | Get a test run's full detail, including scenario results and recommendations |
| apply_voice_test_recommendation | Apply a test run recommendation's quick action to the agent |
| get_voice_test_baseline | Get a voice agent's best-scoring completed run, for regression comparison |
| get_voice_test_score_history | Get completed-run score points for charting |
| list_voice_kb_gaps | List a voice agent's pending knowledge-base gaps from real calls |
| analyze_voice_kb_gaps | Trigger knowledge-base gap analysis over an agent's recent calls |
| add_voice_kb_gap | Write a gap's answer into the agent's knowledge base |
| dismiss_voice_kb_gap | Dismiss a gap without writing anything |
| list_voice_faq_suggestions | List a voice agent's pending FAQ suggestions clustered from real calls |
| generate_voice_faq_suggestions | Trigger FAQ clustering over an agent's recent calls |
| add_voice_faq_suggestion | Write an FAQ suggestion into the agent's knowledge base |
| update_voice_faq_suggestion | Edit a pending FAQ suggestion's question and/or answer |
| dismiss_voice_faq_suggestion | Dismiss an FAQ suggestion without writing anything |
| list_voice_agent_resources | List the documents/links a voice agent searches during calls |
| create_voice_agent_resource | Add one document/link to a voice agent's knowledge base |
| bulk_create_voice_agent_resources | Add up to 100 documents/links in one call |
| update_voice_agent_resource | Partially update a voice agent resource |
| delete_voice_agent_resource | Soft-delete a voice agent resource |
| analyze_voice_instruction_gaps | Advisory-only patch suggestions for an agent's own instructions |
| apply_voice_instruction_gap | Insert a suggested patch into an agent's instructions |
{
"mcpServers": {
"speak-ai": {
"command": "npx",
"args": [
"-y",
"@speakai/mcp-server"
],
"env": {
"SPEAK_API_KEY": "YOUR_SPEAK_API_KEY"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| SPEAK_API_KEY | Declared in the maintainer’s client configuration. | Check documentation |
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.
Enables AI assistants to interact with and manage n8n workflows through natural language.
n8n community node for open-banking.io: API-key auth with client-side, zero-knowledge decryption of your bank accounts, balances and transactions.
A first-party PHP/Laravel Composer package that exposes **QuickBooks Online (QBO)** as a **Model Context Protocol (MCP) server**. AI clients —
Integrate Linear project management with Claude for enhanced workflow automation.
Manage a self-hosted ShareBox tool platform through its MCP CLI integration, with deployment and authentication configured on your own instance.