Fireflies.ai MCP connector
The Fireflies.ai connector brings meeting transcripts, summaries, soundbites and channels into Elaichi, so Claude, ChatGPT, Cursor, Microsoft Copilot or the Elaichi Agent can search and work with recorded meetings as the person who signed in.
- Connects over OAuth
- Free 14-day trial
- No credit card
Summarize yesterday's call with Acme and list every commitment we made.
Working in Fireflies.ai with Elaichi
-
Fireflies search
-
Fireflies get transcripts
-
Fireflies get transcript
How to connect Fireflies.ai to Claude, ChatGPT, Cursor or Microsoft Copilot
Step by step, for each AI app
Fireflies.ai MCP connector for Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
Fireflies.ai MCP connector for Claude Code
-
1
In a terminal, run
claude mcp addwith the endpoint.https://api.elaichi.ai/mcp -
2
Start Claude Code and run
/mcp. -
3
Pick elaichi, then sign in and approve in the browser.
Terminal
$ claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp
Use --scope project instead to share it with the repository through .mcp.json.
Fireflies.ai MCP connector for ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
3
Leave Authentication on OAuth, then tick the risk acknowledgement.
-
4
Press Create, then sign in and approve.
Works on the web. The plugin directory lives at chatgpt.com/plugins.
Fireflies.ai MCP connector for Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
Fireflies.ai MCP connector for Microsoft Copilot
-
1
In Copilot Studio, open your agent, then Tools, Add a tool, New tool and Model Context Protocol.
-
2
Paste the endpoint into Server URL, choose OAuth 2.0, then Dynamic discovery, and press Create.
https://api.elaichi.ai/mcp -
3
Create a new connection, sign in and approve, then press Add to agent.
-
4
Under Channels, open Teams and Microsoft Copilot and make the agent available in Microsoft Copilot.
- Server URL
- https://api.elaichi.ai/mcp
- Authentication
- OAuth 2.0
- Type
- Dynamic discovery
Microsoft Copilot was called Microsoft 365 Copilot. Keep the tool on end-user credentials, so each person signs in as themselves.
Connect Fireflies.ai to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
What teams do with Fireflies.ai through Elaichi
Ask in plain English. Each person’s AI can do only what they’re allowed to, and every action it takes in Fireflies.ai is logged.
-
Sales
Pull the commitments out of a discovery call
After a call ends, ask for the summary and the exact lines where the prospect named a budget or a timeline. Clip the key moment as a soundbite for the deal review.
-
Customer success
Brief yourself before a renewal conversation
Search every recorded meeting with an account and read the summaries side by side. Walk in knowing what was promised last quarter.
-
Support
Find where a customer first described the bug
Search transcripts for the error or feature a customer mentioned and read the exact exchange. Share that meeting with the engineer who picks up the ticket.
-
Product
Turn a week of customer calls into themes
Pull transcripts from the research channel and have the agent group what customers asked for. Create soundbites so the team hears it in the customer's own words.
-
Leadership
See how much time goes to meetings
Ask for meeting analytics by person or group, see which meetings are running right now, and check whether recordings landed in the right channel.
-
Recruiting
Keep interview recordings in the right hands
Rename interview meetings consistently, move them into the hiring channel, and revoke access when a panel member rolls off.
Try asking
- “Summarize yesterday's call with Acme and list every commitment we made.”
- “Find the meeting where the customer mentioned the pricing page bug.”
- “Clip a soundbite of the CFO explaining the budget timeline.”
What connecting Fireflies.ai gets you
6 screens from Elaichi, each doing one job for your Fireflies.ai account.
Ask Elaichi to work across your apps.
Summarize yesterday's call with Acme and list every commitment we made.
Find the meeting where the customer mentioned the pricing page bug.
Clip a soundbite of the CFO explaining the budget timeline.
Also runs in Claude, ChatGPT, Cursor or Microsoft Copilot
The agent
Ask about any recorded meeting in plain language.
Summaries, transcripts and soundbites from Fireflies.ai, answered from live meetings.
Copy the endpoint
AI apps
One endpoint brings Fireflies.ai into every client.
Claude, ChatGPT, Cursor and Microsoft Copilot connect over OAuth, with no SDK and no shared API key.
Tool catalog
19 Fireflies.ai tools, ready without writing code.
Transcripts, summaries, soundbites, channels, analytics and sharing, covered out of the box.
Toolboxes
Every team gets its own Fireflies.ai toolbox.
Sales reads call summaries, product pulls research transcripts, each from a toolbox scoped to them.
Shared connections
Share a Fireflies.ai connection, never a password.
Teammates search meetings through one connection and never see the credential behind it.
Audit log
Every transcript read is on the record.
When, who, what happened and which Fireflies.ai meeting, in an append-only log.
From answering questions to doing the work
A trigger starts the work, inside the same permissions and the same audit log as everything else. Workflows, collections and live dashboards come with the Black plan.
Fireflies.ai digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch meetings
Fireflies.ai
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Jake Morgan
Approve Deny -
Post the digest
Fireflies.ai
Queued
Workflows
Friday's call recap drafts itself and gets approved.
A schedule fetches Fireflies.ai transcripts, groups them, drafts a digest, and posts after one approval.
Fireflies.ai health
Refreshed 4 minutes ago · every 15 minutes · from the meetings collection
Meetings
1,284 ↓ 12%
Transcripts
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Meetings created
Last 14 days
By team
Share of activity
Sales EMEA 34%
Customer success 27%
Support 21%
Product research 18%
Collections and dashboards
Meeting health, computed on a schedule, no asking.
Meetings recorded over 14 days, by team, pulled from Fireflies.ai with no model involved.
Why connect Fireflies.ai's MCP server through Elaichi
Fireflies.ai builds and runs this MCP server. Elaichi sits in front of it, so Fireflies.ai's tools follow the same sign-in, access rules and audit log as every other connector your organization uses. Calls an AI client makes to Fireflies.ai's server directly, outside Elaichi, get none of this.
-
One address for every AI client
Claude, ChatGPT, Cursor and Microsoft Copilot reach Fireflies.ai's tools at the same Elaichi address as every other connected app. Nobody adds Fireflies.ai's server to each client one by one.
-
Each person signs in as themselves
Each person signs in to Elaichi as themselves. Members connect with their own Fireflies.ai sign-in, and a connection someone shares runs on its owner's account. The credential stays in Elaichi's separate credential service, and the AI client holds only its Elaichi sign-in.
-
Rules checked before a call leaves
Restrictions on a role or a person, for the whole connector or a single tool, are checked before a call reaches Fireflies.ai's server. By default, a tool Fireflies.ai does not mark read-only or non-destructive counts as destructive, and over MCP it still runs under the "Use your connected apps" consent.
-
One audit log for every app
Each call that runs is recorded with the person, the tool, the connection and the AI client that made it, in the same audit log as every other app.
-
Tool issues go to Fireflies.ai
Fireflies.ai builds and runs these tools, and Elaichi staff do not curate them, so a report about how a tool behaves goes to the Fireflies.ai team.
For IT and engineering
Elaichi vs Zapier MCP vs Composio for Fireflies.ai
All three can connect Fireflies.ai to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.
| What to check | Elaichi | Zapier MCP | Composio |
|---|---|---|---|
| Where the AI connects |
One address for the whole organization.
https://api.elaichi.ai/mcp
|
A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Fireflies.ai tools | Allow or restrict single Fireflies.ai tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Fireflies.ai call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | Free for one person; $15 per user per month on Gold. | 2 tasks per successful call. | Billed per tool call. |
Sources: Zapier MCP docs, security, usage; Composio docs, gateway, enterprise, pricing. Checked September 2026.
Longer take: Zapier MCP alternative and when you don't need an MCP gateway.
Fireflies.ai tools for your AI agents
19 tools are ready to call through Elaichi's MCP endpoint the moment you connect Fireflies.ai, governed by the same roles, restrictions, and audit log as everything else in Elaichi. Fireflies.ai builds and runs these tools.
No tools match your search.
Questions, answered
How do I connect Fireflies.ai to Claude?
Connect Fireflies.ai in Elaichi first: pick it from the catalog and sign in to your Fireflies.ai account in the window that opens, the same way you log in on the web. There is no OAuth application to register and no client ID or secret to generate. Then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Sign in to Elaichi when Claude asks, and your Fireflies.ai meetings are available.
Does Fireflies.ai work with ChatGPT and Cursor as well as Claude?
Yes. Once Fireflies.ai is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, Microsoft Copilot, any other MCP client and the Elaichi Agent. You connect Fireflies.ai once and every client you use picks it up.
What can an AI agent actually do with my Fireflies.ai data?
It can search your Fireflies.ai meetings, read a transcript or its summary, pull the soundbites from a call, and tell you which meetings are happening right now. It can also rename a meeting, move it into a channel, share it with a colleague or take that access back, and report meeting analytics for a person or group. Short, concrete asks work best, such as the summary of yesterday's call with Acme, rather than a long paragraph of instructions.
Does connecting Fireflies.ai give the AI every meeting in my workspace?
No. The AI sees only the Fireflies.ai meetings, channels and transcripts that the person who signed in can already see, because every request runs as that person. Elaichi can narrow that further with restrictions, and it can never widen it beyond what Fireflies.ai itself allows that person.
Can I stop an agent from sharing or changing meetings in Fireflies.ai?
Yes. Restrictions in Elaichi work per action, so you can allow searching and reading Fireflies.ai transcripts while restricting sharing, renaming, moving or revoking access to meetings. A restricted action still appears in Elaichi's tool search, flagged as restricted, but the AI client cannot run it, whatever the prompt says.
What happens to a Fireflies.ai connection when someone leaves?
Offboarding that person in Elaichi ends their access to Fireflies.ai through every client at once. If they had shared a Fireflies.ai connection with a team, it keeps working for everyone else. Disconnecting Fireflies.ai once in Elaichi removes it from Claude, ChatGPT, Cursor, Microsoft Copilot and every other client together.
Does the Fireflies.ai MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. Fireflies.ai is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, Microsoft Copilot, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.
Is Elaichi an alternative to Zapier MCP for Fireflies.ai?
Yes. Both let Claude, ChatGPT or Cursor use Fireflies.ai. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Fireflies.ai call.
How is Elaichi different from Composio for Fireflies.ai?
Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Fireflies.ai: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put Fireflies.ai in front of your team
14 days of Black, no credit card. Connect it once and pick what each team can call.
When the trial ends, nothing is deleted. You move to the free Personal plan, and connections, roles and the audit log stay where they are.
Add one link to your AI app
The same link for everyone on your team.
https://api.elaichi.ai/mcp
ChatGPT
Claude
Cursor
Microsoft Copilot