Provider REST API

Productivity

Connect Claude to Fireflies.ai

Search meeting transcripts and summaries, share recordings, and send the notetaker to a live call. Toolspoke puts 12 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connection
Provider REST API
Authentication
API key
Actions exposed
12
What a call bills
Nothing
Adapter
Maintained by Toolspoke

Connected in three steps

  1. 1

    Install Fireflies.ai

    Open the marketplace in your workspace, add Fireflies.ai to the project your agents work in, and it appears on the gateway immediately.

  2. 2

    Connect the credential

    Authenticate with api key. Where to get one, and what it has to be able to reach, is the next section.

  3. 3

    Point your agent at the gateway

    Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.

.mcp.json
{
  "mcpServers": {
    "toolspoke": {
      "type": "http",
      "url": "https://toolspoke.com/mcp"
    }
  }
}

One block covers every tool you have installed. Fireflies.ai shows up in the client as soon as your policy allows it, and so does everything else you install later.

Where the address goes, per client

Claude Code

Run it in your project, then /mcp to sign in

claude mcp add --transport http toolspoke https://toolspoke.com/mcp
Claude and Claude Desktop

Settings, then Connectors, then Add custom connector

https://toolspoke.com/mcp
Cursor

~/.cursor/mcp.json, or .cursor/mcp.json for one project

{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }
Codex

~/.codex/config.toml

[mcp_servers.toolspoke]
url = "https://toolspoke.com/mcp"
VS Code

.vscode/mcp.json, or the MCP: Add Server command

{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }

What Fireflies.ai asks for

API key. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.

API keyRequired
Fireflies → Integrations → Fireflies API → copy the API key. The key acts as the user who created it, so it sees that user's meetings plus anything shared with them.

What Claude can do in Fireflies.ai

12 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.

Reads
7Reads
Writes
2Writes
Destructive
3Destructive

Reads

7

Fetches data and changes nothing.

  • get_user

    Read one Fireflies user - name, email, transcript count, minutes used, admin flag and groups. Omit user_id to read the owner of the API key.

  • list_users

    List the users on this Fireflies team with their email, transcript count, minutes used and admin flag.

  • list_transcripts

    Find meetings, newest first, by keyword, date range, organizer, participant or channel. Returns each meeting's id, title, date, duration, people and the short AI summary - not the full transcript; pass an id to get_transcript for that. At most 50 per call; page with skip.

  • get_transcript

    Read one meeting in full - every sentence with speaker and timestamps, the attendees, and the complete AI summary. Large for a long call; use get_transcript_summary when the summary is enough.

  • get_transcript_summary

    Read one meeting's AI summary only - overview, outline, action items, keywords and topics - without the sentence-by-sentence transcript.

  • list_channels

    List the channels meetings are filed into, with their members. A channel id narrows list_transcripts.

  • list_bites

    List soundbites - short clips cut from meetings - with their captions. Give at least one of transcript_id, mine or my_team.

Writes

2

Creates or updates something on the other side.

  • update_meeting_title

    Rename one meeting. Reversible by renaming it again.

  • upload_audio

    Have Fireflies transcribe a recording from a public https URL (mp3, mp4, wav, m4a or ogg). Transcription runs in the background; the new meeting appears in list_transcripts when it finishes.

Destructive

3

Deletes or permanently alters something. Worth granting on purpose.

  • add_to_live_meeting

    Send the Fireflies notetaker into a meeting that is happening now, by its meeting link. Destructive rather than write: the bot joins visibly in front of every participant, including people outside this workspace, and starts recording them - that cannot be taken back once it has happened.

  • share_meeting

    Share one meeting's recording, transcript and notes with email addresses. Destructive because it hands other people's words to whoever is named, including addresses outside the workspace, and they can read it the moment the email arrives.

  • delete_transcript

    Delete one meeting - its recording, transcript and summary. There is no undo.

What it will not do

Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.

It cannot call anything else
The 12 actions above are the whole of it. A call to any other name is refused before it reaches Fireflies.ai rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
It reaches no further than your credential
Toolspoke holds no access to Fireflies.ai of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
It never hears from Fireflies.ai
Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Fireflies.ai. An agent has to ask.
It does not smooth over provider limits
Toolspoke does not retry, queue or back off around Fireflies.ai's own rate limits. A call that Fireflies.ai refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in Fireflies.ai?

12 named actions: 7 that only read, 2 that write and 3 that delete or permanently alter something. They include get_user, list_users and list_transcripts. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.

What credentials does the Fireflies.ai connector need?

API key. The connector asks for api key. Values are encrypted at rest and attached to the outbound request by the gateway, so they are never part of the arguments an agent sends and never reach the audit log.

Does the Fireflies.ai connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 12 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.

What does the Fireflies.ai connector not do?

The 12 actions above are the whole of it. A call to any other name is refused before it reaches Fireflies.ai rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. Toolspoke holds no access to Fireflies.ai of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Fireflies.ai. An agent has to ask. Toolspoke does not retry, queue or back off around Fireflies.ai's own rate limits. A call that Fireflies.ai refuses comes back to the agent as a failed call.

Can I limit which actions an agent can call?

Yes, in two places. The project switches Fireflies.ai's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.

What gets recorded when an agent calls Fireflies.ai?

Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and what the call cost in sandbox time and model tokens. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.