OAuth or API key — which should I use?

OAuth via the Claude Connector listing is the cleanest path for Claude users — no key to rotate and revocation lives in Fireflies. For Cursor, custom clients, or scripted flows where you want a long-lived credential, use the API key from fireflies.ai/dashboard/settings/api with the `mcp-remote` wrapper.

How does it compare to Fellow and Fathom?

All three are first-party remote MCPs that expose the same shape of data (transcripts, summaries, action items). Pick based on which notetaker your team already uses — none of them ingest meetings recorded by a competitor. Fellow is the only one currently flagged as Anthropic-verified.

What is the API rate limit?

Fireflies enforces standard API rate limits per workspace. Tight agent loops that fan out queries can hit them; cache results when summarizing large date ranges.

Can it transcribe live, or only past meetings?

Past meetings only via the MCP. Recording happens in Fireflies itself (calendar bot or browser extension); the MCP queries the resulting transcripts after the call ends.

Fireflies.ai

Name: Top MCPs — curated MCP directory
Creator: Top MCPs
License: https://creativecommons.org/licenses/by/4.0/

Official

Official Fireflies remote MCP — query meeting transcripts, AI summaries, and action items via OAuth or API key.

Score 54(?)Fireflies.aiProprietaryVerified Jun 11, 2026Top MCPs for Meetings & Notes →

Install

Quick answer

What it does

Surfaces Fireflies meeting transcripts, AI-generated summaries, action items, and search across past calls as MCP tools. Hosted by Fireflies; OAuth or API-key authenticated.

Best for

Cross-meeting topic search
AI summaries on demand
Pulling action items into other tools
Sales call recall

Not for

Live in-call assistance
Teams not on Fireflies

Setup recipe

Pick your client, then follow the three steps.

Install

claude_desktop_config.jsonjson

{
  "mcpServers": {
    "fireflies": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://api.fireflies.ai/mcp",
        "--header",
        "\"Authorization:",
        "Bearer",
        "YOUR_FIREFLIES_API_KEY\""
      ],
      "env": {
        "FIREFLIES_API_KEY": "${FIREFLIES_API_KEY}"
      }
    }
  }
}

Paste under mcpServers. Fully quit and reopen Claude after editing.

CLI or .mcp.jsonshell

# export FIREFLIES_API_KEY=your_fireflies_api_key
claude mcp add fireflies -- npx mcp-remote https://api.fireflies.ai/mcp --header "Authorization: Bearer YOUR_FIREFLIES_API_KEY"

Run from your repo. Commit .mcp.json to share with your team.

.cursor/mcp.jsonjson

{
  "mcpServers": {
    "fireflies": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://api.fireflies.ai/mcp",
        "--header",
        "\"Authorization:",
        "Bearer",
        "YOUR_FIREFLIES_API_KEY\""
      ],
      "env": {
        "FIREFLIES_API_KEY": "${FIREFLIES_API_KEY}"
      }
    }
  }
}

Global path: ~/.cursor/mcp.json. Reload window after editing.

.vscode/mcp.jsonjsonc

{
  "servers": {
    "fireflies": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://api.fireflies.ai/mcp",
        "--header",
        "\"Authorization:",
        "Bearer",
        "YOUR_FIREFLIES_API_KEY\""
      ],
      "env": {
        "FIREFLIES_API_KEY": "${FIREFLIES_API_KEY}"
      }
    }
  }
}

VS Code uses the "servers" key (not "mcpServers").

~/.codeium/windsurf/mcp_config.jsonjson

{
  "mcpServers": {
    "fireflies": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://api.fireflies.ai/mcp",
        "--header",
        "\"Authorization:",
        "Bearer",
        "YOUR_FIREFLIES_API_KEY\""
      ],
      "env": {
        "FIREFLIES_API_KEY": "${FIREFLIES_API_KEY}"
      }
    }
  }
}

Open via Cascade → hammer icon → Configure.

cline_mcp_settings.jsonjson

{
  "mcpServers": {
    "fireflies": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://api.fireflies.ai/mcp",
        "--header",
        "\"Authorization:",
        "Bearer",
        "YOUR_FIREFLIES_API_KEY\""
      ],
      "env": {
        "FIREFLIES_API_KEY": "${FIREFLIES_API_KEY}"
      }
    }
  }
}

Open via the Cline sidebar → MCP Servers → Edit.

~/.continue/config.jsonjson

{
  "experimental": {
    "modelContextProtocolServers": [
      {
        "transport": {
          "type": "stdio",
          "command": "npx",
          "args": [
            "mcp-remote",
            "https://api.fireflies.ai/mcp",
            "--header",
            "\"Authorization:",
            "Bearer",
            "YOUR_FIREFLIES_API_KEY\""
          ],
          "env": {
            "FIREFLIES_API_KEY": "${FIREFLIES_API_KEY}"
          }
        }
      }
    ]
  }
}

Continue uses modelContextProtocolServers with a transport block.

~/.codex/config.tomlshell

# ~/.codex/config.toml
[mcp_servers.fireflies]
command = "npx"
args = [
  "mcp-remote",
  "https://api.fireflies.ai/mcp",
  "--header",
  "\"Authorization:",
  "Bearer",
  "YOUR_FIREFLIES_API_KEY\"",
]
env = { FIREFLIES_API_KEY = "${FIREFLIES_API_KEY}" }

Codex uses TOML. Each server is a [mcp_servers.<name>] subtable.

~/.config/zed/settings.jsonjsonc

{
  "context_servers": {
    "fireflies": {
      "command": {
        "path": "npx",
        "args": [
          "mcp-remote",
          "https://api.fireflies.ai/mcp",
          "--header",
          "\"Authorization:",
          "Bearer",
          "YOUR_FIREFLIES_API_KEY\""
        ]
      },
      "env": {
        "FIREFLIES_API_KEY": "${FIREFLIES_API_KEY}"
      }
    }
  }
}

Zed calls them "context_servers". Settings live-reload on save.

ChatGPT → Settings → Connectors (remote URL)json

{
  "name": "Fireflies.ai",
  "transport": "http",
  "url": "https://api.fireflies.ai/mcp"
}

Paste this into Settings → Connectors → Add custom connector. Requires ChatGPT Pro / Team / Enterprise / Edu with Developer mode enabled. ChatGPT supports remote HTTPS MCP servers only — stdio servers must be hosted on a public HTTPS endpoint first.

2
Set required secrets
Set FIREFLIES_API_KEY in your shell environment before launching your MCP client.
3
Try a minimum working prompt
Pull every customer call where pricing came up
Using the Fireflies connector, find every customer call from the last 30 days where pricing or budget came up. For each, give me the meeting title, the date, and a two-sentence summary of the pricing discussion.
Tested with: Claude Desktop, Cursor.

Tools & permissions

Tools list pending verification. The server exposes tools over MCP; we haven’t yet parsed its capability manifest into this page. Check the GitHub repo for the authoritative list.

Security & scope

Access scope: Read-only
Sandbox: Hosted by Fireflies. OAuth or Bearer-token scoped to the connecting user. No local recording or file access.
Gotchas: API keys grant access to every meeting the user can see — rotate if a developer with a personal key leaves the team.
Workspace admins can disable third-party API access globally; if calls return 401, check workspace settings before debugging the client.

Agent prompt pack

— copy into Claude, Cursor, or ChatGPT.

Paste into Claude, Cursor, or ChatGPT. Edit the [brackets] before sending.

Recommend the best MCP servers for [task: e.g. meetings & notes work] in [client: Claude].

Constraints:
- Prefer tools that are [official | open-source | read-only] — pick what matters for my use case.
- Exclude MCPs that require [e.g. a paid plan, OAuth-only flows, remote-only transport].
- Return at most 3 picks, ranked.

For each pick include:
1. One-sentence rationale.
2. The ready-to-paste install snippet for my client.
3. Any required secrets I need to create before installing.

Cross-check the top-mcps.com listing: https://top-mcps.com/top-mcps-for-meeting-notes

Compare Fireflies.ai against a real alternative. Swap the second MCP in [brackets] if you want a different match.

Compare Fireflies.ai MCP vs [Fellow MCP] for the following job: [describe the job, e.g. "let an agent create GitHub issues on bug triage"].

Judge them on:
- Setup time and complexity (what a new user hits first).
- Auth model (none / API key / OAuth 2.1) and credential risk.
- Transport (stdio / Streamable HTTP / SSE) and where the server runs.
- Required secrets and the blast radius if they leak.
- Operational risk in an unattended agent loop.
- Which one is "good enough" for a weekend prototype vs. production.

End with one sentence: which should I pick for my scenario, which is: [my scenario].

References:
- https://top-mcps.com/mcp/fireflies
- top-mcps.com listing for Fellow

Asks the agent to install and verify. Works inside Claude Code, Cursor Agent, Codex CLI.

Install the Fireflies.ai MCP server for my [client: Claude] at the default config path for that client.

Use the exact install snippet published at https://top-mcps.com/mcp/fireflies (fetch https://top-mcps.com/mcp/fireflies.json for the canonical server.json if you can read URLs).

Before finishing:
1. Create the required secrets (FIREFLIES_API_KEY) and put them in the appropriate env block — do not hard-code them.
2. Restart or reload the client so it picks up the new server.
3. Verify the server is connected (green / running state) and at least one tool is listed.
4. If anything fails, read the client's MCP logs and report the exact error — do not silently retry.

Confirm when done and list the tools the server now exposes.

Frequently asked questions

What changed

— 2 updates tracked.

Jun 11, 2026
Refreshed install snippets and fact sheet; verified for 2026.
Oct 1, 2025
Initial directory listing.

At a glance

Maintainer: Fireflies.ai
Transport: Streamable HTTP
Auth model: OAuth 2.1
Required secrets: FIREFLIES_API_KEY
Supported clients: ChatGPT
Claude Desktop
Claude Code
Cursor
VS Code
Windsurf
Cline
Continue
Zed
Codex CLI
License: Proprietary
Language: —
Latest version: —
Last verified: Jun 11, 2026

Official website

Alternatives

Fellow →
Anthropic-verified Fellow Connector — query meeting notes, transcripts, action items, and calendar events from Claude.
Fathom →
Official Fathom remote MCP — access meeting recordings, transcripts, summaries, and webhooks from any MCP client.
Granola →
Mac-native AI notepad that captures meetings via system audio (no bot) — query your past notes from ChatGPT.
Circleback →
AI notetaker for sales and customer teams — query past meetings and push action items into your CRM from inside ChatGPT.

More Meetings & Notes MCPs

Other tools in the same category worth evaluating.

Fellow

Official

Anthropic-verified Fellow Connector — query meeting notes, transcripts, action items, and calendar events from Claude.

fellowmeeting-notestranscriptsaction-items

< 1 minLow

Fathom

Official

Official Fathom remote MCP — access meeting recordings, transcripts, summaries, and webhooks from any MCP client.

fathommeeting-notestranscriptsrecordings

2 minLow

Compared with Fireflies.ai

Side-by-side breakdowns for the choices people most often weigh against this MCP.

Fireflies.aivsFellow Fireflies.aivsFathom Fireflies.aivsGranola Fireflies.aivsCircleback

Exploring Top MCPs for Meetings & Notes? See all Meetings & Notes MCPs →

Quick answer

What it does

Best for

Not for

Setup recipe

Install

Set required secrets

Try a minimum working prompt

Tools & permissions

Security & scope

Agent prompt pack

Full details

Frequently asked questions

OAuth or API key — which should I use?

How does it compare to Fellow and Fathom?

What is the API rate limit?

Can it transcribe live, or only past meetings?

What changed

More Meetings & Notes MCPs

Fellow

Fathom

Compared with Fireflies.ai