Speak Ai MCP server
Yes. Speak Ai publishes an official MCP server at https://api.speakai.co/v1/mcp. It's hosted, or you can run it on your own computer, and lets you sign in with your Speak Ai account. It offers 119 tools. We last checked it on 22 Nov 2026.
Official: answers MCP requests at api.speakai.co, on Speak Ai's own domain speakai.co. Checked 22 Nov 2026. Maintained by Stuart Brameld.
Key facts
As of 22 Nov 2026, Speak Ai's official MCP server scores 91/100 on MartechDB's Agent Readiness Index (v1.1), joint 11th of 28 in Meeting notetakers. It answered 55 of our 55 checks in the last 90 days and has 119 tools named in its documentation.
How the Agent Readiness Index works · Wrong? Suggest a correction
Speak Ai MCP server review
91/100
Speak Ai's Speak AI scores 91/100 on MartechDB's Agent Readiness Index: one of the easiest marketing tools to connect an AI agent to. That ranks it joint 11th of 28 in Meeting notetakers.
The good
Hosted by Speak Ai: connect by URL, with nothing to install
Sign in with your Speak Ai account: your AI client sets up the sign-in itself, with no API key
Documented, with 119 tools known
Published to the official MCP Registry
Answered 100% of our checks in the last 90 days
Free trial
No card needed to start
The bad
Nothing we've found.
Official MCP server
Speak AI
Search recordings, summarize meetings, create clips, and automate workflows from your AI assistant.
- Address
- https://api.speakai.co/v1/mcp
- npm package
- @speakai/mcp-server
- Runs
- Hosted or install locally
- Sign-in
- Cost to use
- Plan: Pay as You Go · Free trial · No card needed5 requests per 30 seconds on authentication endpointsFrom Speak Ai's own page, limits from this page
- Official MCP Registry
-
Listed as
io.github.speakai/mcp-server· published 28 Aug 2026 - How we know it's official
-
- Answers MCP requests at api.speakai.co, on Speak Ai's own domain speakai.co.
- Published in the official MCP Registry as io.github.speakai/mcp-server, from the speakai GitHub account.
- Documentation
- docs.speakai.co/mcp
- Source code
- github.com/speakai/speakai-mcp
- Tools
- 119 tools · from Speak Ai's documentation
- First seen
- 28 Aug 2026
- Last checked
-
Reachable ·
16 Nov 2026: reachable17 Nov 2026: reachable18 Nov 2026: reachable19 Nov 2026: reachable20 Nov 2026: reachable21 Nov 2026: reachable22 Nov 2026: reachable
- Uptime
- 100% · 55 of 55 checks reachable since 1 Oct 2026
Speak AI tools (119)
The server needs sign-in before it lists its tools, so these are as Speak Ai's documentation names them (read 4 Oct 2026). They may be out of date.
-
update_transcriptionEdit the official transcript text of a single media file by finding and replacing text.
-
get_signed_upload_urlGet a pre-signed S3 URL for direct file upload to Speak AI storage.
-
upload_mediaUpload media from a URL: a direct/public file URL, a pre-signed S3 URL, or a shareable social/video page link, which Speak resolves to the underlying media automatically.
-
upload_local_fileUpload a local file to Speak AI for transcription and analysis.
-
upload_and_analyzeUpload and transcribe media from a URL: a direct/public file URL, OR a shareable social/video page link, which Speak resolves to the underlying media automatically.
-
list_mediaList and search media files in the workspace with filtering, pagination, and sorting.
-
get_media_insightsRetrieve AI-generated insights for a processed media file: topics, sentiment, keywords, action items, summaries, and more.
-
get_transcriptRetrieve the full transcript for a media file with speaker labels and timestamps.
-
get_captionsGet captions for a media file.
-
update_transcript_speakersUpdate or rename speaker labels in a single media transcript.
-
bulk_update_transcript_speakersNormalise speaker names that are ALREADY correct across multiple media files: for example changing "Frederik S." to "Frederik" everywhere.
-
get_media_statusCheck the processing status of a media file.
-
update_media_metadataUpdate metadata fields (name, description, tags, status) for an existing media file.
-
delete_mediaPermanently delete a media file and all associated transcripts and insights.
-
toggle_media_favoriteMark or unmark media files as favorites for quick access.
-
reanalyze_mediaRe-run AI analysis on a media file using the latest models.
-
bulk_move_mediaMove multiple media files to a folder in a single operation.
-
upload_and_analyze_batchUpload several URLs in one call: the batch form of upload_and_analyze, for when someone hands you a list of links.
-
ask_ai_chatAsk an AI-powered question about your media using Speak AI's AI Chat.
-
retry_ai_chatRetry a failed or incomplete AI Chat response.
-
get_chat_historyGet a list of recent AI Chat conversations.
-
get_chat_messagesGet full message history for conversations.
-
delete_chat_messageDelete a specific chat message from conversation history.
-
list_promptsList all available AI Chat templates.
-
get_favorite_promptsGet all prompts and answers that have been marked as favorites.
-
toggle_prompt_favoriteMark or unmark a chat message as a favorite for easy retrieval later.
-
update_chat_titleUpdate the title of a chat conversation for easier identification in history.
-
submit_chat_feedbackSubmit feedback on a chat response (thumbs up/down).
-
get_chat_statisticsGet usage statistics for AI Chat / chat.
-
export_chat_answerExport a specific AI Chat answer.
-
get_analysis_quoteCheck whether a media file can be analysed as audio or video, and what it will cost, before running ask_ai_chat with analysisInput.
-
search_mediaDeep search across all media transcripts, insights, and metadata.
-
get_media_statisticsGet workspace-level media statistics: total counts, processing status breakdown, storage usage, etc.
-
list_supported_languagesList all languages supported for transcription.
-
list_foldersList all folders in the workspace with pagination and sorting.
-
get_folder_infoGet detailed information about a specific folder including its contents.
-
create_folderCreate a new folder in the workspace.
-
clone_folderDuplicate an existing folder and all of its contents.
-
update_folderUpdate a folder.
-
delete_folderPermanently delete a folder.
-
get_all_folder_viewsRetrieve all saved views across all folders.
-
get_folder_viewsRetrieve all saved views for a specific folder.
-
create_folder_viewCreate a new saved view for a folder with a custom set of display columns.
-
update_folder_viewUpdate an existing saved view.
-
clone_folder_viewDuplicate an existing folder view into a target folder.
-
create_recorderCreate a new recorder or survey for collecting audio/video submissions.
-
list_recordersList all recorders/surveys in the workspace.
-
get_recorder_infoGet detailed information about a specific recorder including its settings and questions.
-
clone_recorderDuplicate an existing recorder including all its settings and questions.
-
get_recorder_recordingsList all submissions/recordings collected by a specific recorder.
-
generate_recorder_urlRetrieve the existing shareable URL and embed iframe code for a recorder/survey.
-
update_recorder_settingsUpdate configuration settings for a recorder (branding, capture options, etc.).
-
update_recorder_questionsUpdate the survey questions and respondent-info settings for a recorder.
-
check_recorder_statusCheck whether a recorder/survey is active and accepting submissions.
-
delete_recorderPermanently delete a recorder/survey.
-
create_clipCreate a highlight clip from one or more media files by specifying time ranges.
-
get_clipsList clips, optionally filtered by folder or media files.
-
update_clipUpdate a clip's title, description, or tags.
-
delete_clipPermanently delete a clip and its associated media file.
-
export_mediaExport a media file's transcript or insights in various formats (pdf, docx, srt, vtt, txt, csv).
-
export_multiple_mediaExport multiple media files at once, optionally merged into a single file.
-
list_meeting_eventsList scheduled or completed meeting assistant events with filtering and pagination.
-
schedule_meeting_eventSchedule the Speak AI meeting assistant to join and record an upcoming meeting.
-
remove_assistant_from_meetingRemove the Speak AI assistant from an active or scheduled meeting.
-
delete_scheduled_assistantCancel and delete a scheduled meeting assistant event.
-
get_live_meeting_transcriptFetch new sentences from an in-progress or just-ended meeting transcript.
-
list_automationsList automation rules in the workspace, with paging and filters.
-
get_automationGet detailed information about a specific automation rule, including its trigger and step graph.
-
create_automationCreate a new automation rule using the V2 graph model (trigger + ordered steps).
-
update_automationUpdate an existing automation rule.
-
toggle_automation_statusToggle an automation rule between active and inactive.
-
list_automation_namesList automations as lightweight { name, id } pairs: useful for pickers without fetching full configs.
-
get_automation_runsGet the run history (executions) for an automation, with paging and optional status filter.
-
bulk_update_automation_statusActivate or deactivate multiple automations at once.
-
bulk_assign_automation_foldersSet the folder scope for multiple automations at once.
-
run_automationsManually run one or more automations against one or more media items now (outside the normal trigger).
-
delete_automationPermanently delete an automation rule.
-
list_automation_appsList the apps available in the automation catalog (e.g. Speak native + connected integrations).
-
list_automation_triggersList the trigger types available in the automation catalog.
-
list_automation_actionsList the action/step types available in the automation catalog.
-
build_automationHigh-level automation builder: create (or update) a Speak automation from a friendly spec without knowing the wire format.
-
get_automation_runGet one automation run in full: every step, in dependency order, with what it produced and why it stopped.
-
get_automation_run_statsAggregate run counts for an automation over a period: how many completed, failed, or were stopped.
-
test_automationRun an automation once against one media item to see which way it branches.
-
validate_automation_graphCheck a step graph without saving anything.
-
describe_automation_graphShow a saved automation's steps as an indented branch tree instead of a flat list.
-
create_webhookCreate a new webhook to receive real-time notifications when events occur in Speak AI.
-
list_webhooksList all configured webhooks in the workspace.
-
update_webhookUpdate an existing webhook.
-
delete_webhookDelete a webhook and stop receiving notifications at its endpoint.
-
provision_inbound_webhookProvision a standalone inbound webhook and get its public receive URL (inboundUrl) BEFORE creating an automation.
-
get_inbound_webhookGet an inbound webhook's public receive URL, captured sample payload, and the ready-to-paste trigger payload tokens for mapping payload values into automation steps.
-
get_webhook_attemptsGet the delivery log for an inbound webhook: each received request with its HTTP acknowledgement status and the automation run it started.
-
create_text_noteCreate a new text note in Speak AI for analysis.
-
get_text_insightRetrieve AI-generated insights for a text note, including topics, sentiment, summaries, and action items.
-
reanalyze_textTrigger a re-analysis of an existing text note to regenerate insights with the latest AI models.
-
update_text_noteUpdate an existing text note's name, content, or metadata.
-
list_fieldsList all custom fields defined in the workspace.
-
create_fieldCreate a new custom field for categorizing and tagging media.
-
update_fieldUpdate a specific custom field by ID.
-
update_multiple_fieldsSet custom field values across media in a single batch operation.
-
create_embedCreate an embeddable player/transcript widget for a media file or a set of folders.
-
update_embedUpdate an existing embed widget: appearance/feature toggles via meta, plus scope and privacy.
-
check_embedCheck if an embed exists for a media file and retrieve its configuration.
-
get_embed_iframe_urlGet the iframe URL for embedding a media player/transcript on a webpage.
-
list_usersList the users (members) in the workspace/company, with their ids, names, emails, and permissions.
-
list_user_groupsList all user groups in the company.
-
create_user_groupCreate a new user group and assign members.
-
update_user_groupUpdate a user group's name and member list.
-
delete_user_groupDelete a user group.
-
list_dashboard_widgetsDiscovery + how-to helper for building and customizing dashboards.
-
list_dashboardsList all analytics dashboards the caller can access, including share state and each dashboard's current revision (needed for update_dashboard).
-
get_dashboardGet a single dashboard's full spec: title, description, source, date range, sections, widgets, and the current revision (pass that revision back to update_dashboard).
-
create_dashboardCreate an analytics dashboard.
-
update_dashboardUpdate a dashboard.
-
delete_dashboardSoft-delete a dashboard.
-
duplicate_dashboardClone an existing dashboard.
-
share_dashboardEnable public sharing for a dashboard and return its share token + embed id.
-
get_dashboard_speakers_insightCompute a speakers breakdown for a given folder scope, date range, and field filters.
Connect your AI to Speak Ai
Add the official Speak Ai MCP server to Claude, ChatGPT or your editor.
Connect Speak Ai MCP to Claude
Claude.ai and Claude Desktop
Open Customize, then Connectors.
Click +, then Add custom connector.
Name it Speak Ai, paste the address below and click Add.
Connect Speak Ai MCP to ChatGPT
Open Settings, then Apps, then Advanced settings.
Turn on Developer mode, then click Create.
Name it Speak Ai and paste the address below.
Connect Speak Ai MCP to Cursor
Opens Cursor if it's installed. If nothing happens, use the JSON below.
Connect Speak Ai MCP to VS Code
Opens VS Code if it's installed. Otherwise add the JSON settings from the Cursor tab to your .vscode/mcp.json.
Speak Ai MCP server questions
Does Speak Ai have an official MCP server?
Yes. Speak Ai publishes its MCP server itself. Its address is on Speak Ai's own domain (api.speakai.co). MartechDB only lists servers a vendor publishes, never community copies.
What is the Speak Ai MCP server URL?
The address is https://api.speakai.co/v1/mcp.
Does the Speak Ai MCP server need an API key?
No. You sign in with your Speak Ai account (OAuth), and your AI client handles the rest.
How do I connect Speak Ai MCP to Claude, ChatGPT or Cursor?
In Claude, add https://api.speakai.co/v1/mcp as a custom connector (Customize, Connectors, Add custom connector). In ChatGPT, turn on developer mode (Settings, Apps, Advanced settings) and create an app with the same address. In Cursor, use the Add to Cursor link on MartechDB's page, or paste the JSON settings into your mcp.json. In Claude Code, run: claude mcp add --transport http speak-ai https://api.speakai.co/v1/mcp
What can the Speak Ai MCP server do?
It offers 119 tools, including update_transcription, get_signed_upload_url, upload_media, upload_local_file and upload_and_analyze (as its documentation names them, read on 4 Oct 2026).
Is the Speak Ai MCP server in the official MCP Registry?
Yes, as io.github.speakai/mcp-server.
Is the Speak Ai MCP server working?
Yes. It answered our most recent check. We last checked it on 22 Nov 2026.
What are the alternatives to Speak Ai's MCP server?
In Meeting notetakers, the most agent-friendly alternatives with an official MCP server are Otter.ai (98/100), Bridge (97/100), Avoma (97/100), Praiz (95/100) and Wave AI Note Taker (95/100). Speak Ai scores 91/100 on the same index.
Alternatives to Speak Ai's MCP server
Vendors in Meeting notetakers with an official MCP server, the most agent-friendly first. Speak Ai scores 91/100.
Compare all 38 Meeting notetakers vendors →Use with AI
Connect your AI to MartechDB
Then ask it about Speak Ai, or any of the 1,850 marketing tools with an official MCP server. Free, no sign-in.
Claude.ai and Claude Desktop
Open Customize, then Connectors.
Click +, then Add custom connector.
Name it MartechDB, paste the address below and click Add. There's no sign-in.
The free plan allows one custom connector. On Team and Enterprise plans, an owner adds the connector first.
Claude Code
Run this in your terminal:
ChatGPT
Open Settings, then Apps, then Advanced settings.
Turn on Developer mode, then click Create.
Name it MartechDB, paste the address below and choose No authentication.
Developer mode is on Plus and Pro plans, and on Business, Enterprise and Edu if an admin allows it.
API
The same data as JSON, with no sign-in. See the OpenAPI description for every endpoint and field.
CLI
Search the directory and print the command to connect a vendor's server, from your terminal. Needs Node 18 or later. View on npm
Show that your MCP server is verified
If you work at Speak Ai, add this badge to your MCP docs or README. It's free, it's the same for every vendor, and it updates from our daily checks: it shows uptime while the server responds, and says so if it stops.
Something wrong or out of date? Suggest a correction or email us, and we'll check it against the evidence. Every correction we make is listed on Corrections.