Fireflies MCP connector for AI agents

CALL ANY TOOL

Search transcripts, retrieve recordings, create soundbites, and access meeting analytics. Same toolkit, every framework, no auth plumbing.

fireflies_transcripts_search

Search transcripts

Search meeting transcripts across the workspace by keyword, speaker, date, or channel.

Parameters

Name

Type

Required

Description

query

string

Optional

Keyword or phrase to search in transcripts

from_date

string

Optional

Start date (ISO 8601)

to_date

string

Optional

End date (ISO 8601)

limit

integer

Optional

Max meetings to return

fireflies_transcript_get

Get transcript

fireflies_meetings_list

List meetings

fireflies_soundbites_create

Create soundbite

fireflies_analytics_get

Get analytics

Build your Agent

Drop the toolkit in, point it at the user, and your agent can search Fireflies transcripts and retrieve meeting summaries from the first run.

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["firefliesmcp"], toolNames: ["fireflies_transcripts_search", "fireflies_transcript_get", "fireflies_meetings_list"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["firefliesmcp"], toolNames: ["fireflies_transcripts_search", "fireflies_transcript_get", "fireflies_meetings_list"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["firefliesmcp"], toolNames: ["fireflies_transcripts_search", "fireflies_transcript_get", "fireflies_meetings_list"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/firefliesmcp",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your meeting agent to start pulling meeting intelligence from Fireflies.

Search & recall

Copy the prompt

Copied

Find all meetings where [topic] was discussed this quarter.

Copy the prompt

Copied

Get the transcript and summary for my meeting with [person] on [date].

Copy the prompt

Copied

List all meetings from the last [N] days.

Action & create

Copy the prompt

Copied

Create a soundbite from the moment [description] in meeting [ID].

Copy the prompt

Copied

Get meeting analytics for my team this month.

Copy the prompt

Copied

Summarize recurring themes across all customer calls this week.

SEE HOW AUTH WORKS

Users authorize Fireflies once. Their workspace credentials stay vaulted, every transcript access is scoped to their account, and every call is logged.

1

Authorize

Your user connects

Fireflies MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

2

Store

Their

Fireflies MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

3

Resolve

When your agent calls a

Fireflies MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

4

Audit

Every

Fireflies MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

Same per-user auth pattern across other transcription and meeting intelligence connectors.

No items found.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.

// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Fireflies MCP today. Others tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Fireflies as the user or a shared account?

As the user. Each workspace member authorizes once and Scalekit resolves their credential. Transcript access is scoped to that user's Fireflies workspace.

Where is the Fireflies OAuth token stored?

In Scalekit's AES-256 vault, namespaced per tenant. Tokens never appear in prompts or LLM context.

Can I prevent the agent from accessing specific meetings?

Yes. Fireflies workspace permissions apply per user. Scalekit enforces credentials and audits all transcript access on top.

What happens when a user revokes Fireflies access?

The connection is invalidated on the next tool call. Subsequent requests fail closed. Other workspace members remain unaffected.

Can the agent create Linear tasks from Fireflies action items?

Yes. A single agent can pull Fireflies action items and create Linear issues in the same workflow, using the same user identity for both connectors.

Fireflies MCP

Tools your agent reaches for on Fireflies MCP, scoped per user.