SafetyExecution & processesConnect only meetings and workspaces intended for AI review, especially when transcripts include customers or internal discussions.
PrivacyExecution & processesMeeting transcripts, summaries, speaker names, attendee metadata, and conversation details may be sent through model context.
Safety notes
Connect only meetings and workspaces intended for AI review, especially when transcripts include customers or internal discussions.
Privacy notes
Meeting transcripts, summaries, speaker names, attendee metadata, and conversation details may be sent through model context.
Prerequisites
Fireflies.ai account (sign up at https://fireflies.ai if needed)
Fireflies API key (obtain from Fireflies settings/API section)
OAuth authentication support (for workspace access)
HTTP transport support (remote MCP server at https://api.fireflies.ai/mcp)
Claude Desktop 0.7.0+ or Claude Code with MCP support
Internet connection (remote API access required)
Understanding of rate limits (Free/Pro: 50 requests/day, Business/Enterprise: 60 requests/minute)
Workspace permissions (viewer or higher role for accessing meetings in Fireflies workspace)
Understanding of meeting privacy settings (meetings must allow API access)
Understanding of Fireflies workspace structure and meeting organization
Unlock the power of your meeting data by connecting Claude to Fireflies.ai's meeting intelligence platform. Automatically extract action items, search conversation history, analyze speaker participation, and generate comprehensive meeting summaries through natural language commands, transforming how you capture and act on meeting insights.
Features
Access meeting transcripts and recordings
Retrieve automated meeting summaries
Search conversation content
Extract action items and decisions
Analyze speaker analytics and participation
Advanced Fireflies meeting transcription and analysis with AI-powered insights, action item extraction, and meeting summary generation
Batch operations support for efficient bulk meeting processing, transcript analysis, and data export with automatic rate limit handling and retry logic
Real-time meeting synchronization capabilities with webhook integration support for monitoring new meetings and triggering automated workflows
Use Cases
Review meeting outcomes and decisions
Extract action items for follow-up
Search past discussions by topic
Generate meeting reports for stakeholders
Track speaker participation metrics
Build automated meeting management workflows that sync external systems with Fireflies for real-time meeting transcription and analysis
Fireflies API keys and access tokens must be securely stored and never exposed in client-side code or public repositories - use environment variables and secure credential management
Fireflies OAuth access tokens should be used for third-party integrations to ensure proper access control, token lifecycle management, and automatic token refresh
Fireflies meeting IDs and transcript data may contain sensitive business information and personal conversations - ensure Fireflies resource identifiers are kept private and not shared in public configurations
Rate limiting and API quota management are critical for Fireflies MCP servers - implement proper rate limit handling, retry logic, and quota monitoring to prevent service disruption
Fireflies webhook configurations and payloads may contain sensitive meeting transcripts and participant information - ensure webhook endpoints are properly secured with authentication and HTTPS encryption
Troubleshooting
Too many requests error with code 429
Free/Pro plans: 50 requests/day limit. Business/Enterprise: 60 requests/minute. Check retryAfter timestamp in error response. Wait specified time before retry or upgrade plan for higher limits.
Invalid API key or authentication failed error
Add Authorization header with Bearer YOUR_API_KEY format. Verify API key hasn't expired in Fireflies settings. Check for typos and regenerate key if authentication continues to fail.
Cannot access meeting transcripts or recordings
Verify workspace permissions grant access to meetings. Check meeting privacy settings allow API access. Ensure your account has viewer or higher role for target meetings in Fireflies workspace.
Transcripts incomplete or missing sections
Check audio quality of original recording. Verify storage limits haven't been exceeded for your plan tier. Review transcript settings for language and accuracy preferences in Fireflies workspace.
Fireflies MCP server authentication errors with API keys
Verify API key is valid and not expired. Check API key permissions match required operations. Ensure API key format is correct (Bearer token in Authorization header). For OAuth integrations, verify token refresh logic is working correctly.
Fireflies rate limit errors when processing multiple meetings
Implement exponential backoff retry logic with jitter. Use Fireflies API rate limit headers to monitor usage. Reduce concurrent requests. Cache frequently accessed meeting data. Fireflies allows 100 requests per minute per API key.
Fireflies meeting or transcript access denied errors
Verify API key has access to the meeting. Check meeting permissions and account membership. Ensure API key has required permissions (read transcripts, read meetings) for target operations.
Fireflies MCP server connection timeouts or network errors
Check network connectivity and firewall settings. Verify Fireflies API endpoints are accessible. Increase request timeout values. Implement connection pooling and retry mechanisms with exponential backoff.
Show that Fireflies MCP Server for Claude is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/mcp/fireflies-mcp-server)
How it compares
Fireflies MCP Server for Claude side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
3 trust signals differ across this comparison (Package trust, Source provenance, Submitter).
✓Connect only meetings and workspaces intended for AI review, especially when transcripts include customers or internal discussions.
✓Vexa MCP can request bots to join meetings, stop bots, parse meeting links, read transcripts, manage recordings, create transcript share links, send and read meeting chat, make the bot speak, share screen content, update bot config, connect calendars, and configure webhooks.
Meeting URLs, IDs, passcodes, bot names, platform names, participant data, recordings, transcript share links, and API keys require careful handling.
Public transcript share links and recording download URLs should be short-lived and shared only with approved recipients.
Interactive bot tools can visibly act in live meetings; require human approval before using chat, speech, or screen-sharing tools.
The service README includes a DoD table that marks several MCP checks as untested, so validate the exact deployment path before production use.
✓Share only intended Notion pages or databases and review writes that alter docs, tasks, or workspace records.
✓Restrict the Airtable API key to the bases and write scopes Claude is allowed to use before enabling record or schema changes.
Privacy notes
✓Meeting transcripts, summaries, speaker names, attendee metadata, and conversation details may be sent through model context.
✓Audio, transcripts, speaker labels, meeting metadata, chat messages, recordings, screenshots, participant names, calendar events, webhook payloads, meeting notes, API keys, and tool results may be visible to the MCP client and model provider.
Hosted Vexa sends meeting data to Vexa-operated infrastructure; self-hosted deployments still may use hosted transcription tokens unless fully self-hosting transcription.
Browser bot sessions can persist authenticated browser state through storage such as S3-compatible backends.
Logs, databases, object storage, share links, webhook receivers, and AI prompts can retain sensitive meeting content after a call ends.
✓Page contents, database rows, comments, attachments, user names, and workspace metadata may be sent through model context.
✓Airtable records, field values, attachments, and base metadata may be sent through the MCP client and model context.
Prerequisites
Fireflies.ai account (sign up at https://fireflies.ai if needed)
Fireflies API key (obtain from Fireflies settings/API section)
OAuth authentication support (for workspace access)
HTTP transport support (remote MCP server at https://api.fireflies.ai/mcp)
Node.js and npx available for the `mcp-remote` client bridge.
Vexa API key for hosted Vexa or an approved self-hosted Vexa deployment.
Meeting organizer permission and participant consent before joining, recording, transcribing, chatting, speaking, or screen-sharing through a bot.
Platform policy review for Google Meet, Microsoft Teams, and Zoom bot participation.