Fathom MCP | Bearer Token Fathom connector for AI agents

Tools your meeting intelligence agent reaches for on Fathom, scoped per user.

CALL ANY TOOL

List calls, fetch transcripts, retrieve AI summaries, and pull action items from recorded meetings.

fathom_list_teams

List teams

List all teams configured in Fathom. Returns team names and metadata. Use the returned team names to filter meetings via the teams parameter in the List Meetings tool.

Parameters

Name

Type

Required

Description

cursor

string

Optional

Pagination cursor returned by a previous List Teams response. Pass this value to retrieve the next page of results.

fathom_get_recording_summary

Get recording summary

fathom_list_users

List users

fathom_get_recording_transcript

Get recording transcript

fathom_list_meetings

List meetings

List meetings recorded by Fathom with optional filters. Returns paginated meeting records including participants, recording IDs, and metadata. Use cursor for pagination. Array parameters (calendar_invitees_domains, recorded_by, teams) must be sent with bracket notation (e.g., calendar_invitees_domains[]=example.com) : the API handles this automatically when you pass arrays.

Parameters

Name

Type

Required

Description

calendar_invitees_domains

array

Optional

Filter meetings by company domains of calendar invitees. Provide as an array of domain strings, e.g. ["acme.com", "example.org"]. Sent as calendar_invitees_domains[] query params.

calendar_invitees_domains_type

string

Optional

Controls how the calendar_invitees_domains filter is applied. Valid values: all (all invitees match), only_internal (only internal domains), one_or_more_external (at least one external domain).

created_after

string

Optional

Return only meetings created after this ISO 8601 datetime. Example: 2025-01-01T00:00:00Z.

created_before

string

Optional

Return only meetings created before this ISO 8601 datetime. Example: 2025-12-31T23:59:59Z.

cursor

string

Optional

Pagination cursor returned by a previous List Meetings response. Pass this value to retrieve the next page of results.

include_action_items

boolean

Optional

When true, each meeting record includes extracted action items from the AI analysis.

include_crm_matches

boolean

Optional

When true, each meeting record includes matched CRM data (contacts, deals, companies).

include_highlights

boolean

Optional

When true, each meeting record includes AI-generated highlights from the recording.

include_summary

boolean

Optional

When true, each meeting record includes the AI-generated meeting summary.

include_transcript

boolean

Optional

When true, each meeting record includes the full meeting transcript.

meeting_type

string

Optional

Filter meetings by their meeting type name (e.g., 'Sales Call', 'Demo'). Must match a meeting type name configured in Fathom.

recorded_by

array

Optional

Filter meetings by recorder email addresses. Provide as an array of email strings. Sent as recorded_by[] query params.

teams

array

Optional

Filter meetings by team names. Provide as an array of team name strings. Sent as teams[] query params.

fathom_get_recording_download_status

Get recording download status

fathom_list_team_members

List team members

fathom_create_webhook

Create webhook

fathom_list_meeting_types

List meeting types

fathom_request_recording_download

Request recording download

fathom_delete_webhook

Delete webhook

Build your Agent

Drop the toolkit in, point it at the user, and your meeting intelligence agent can use Fathom 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: ["fathom"], toolNames: ["fathom_calls_list", "fathom_call_get", "fathom_call_transcript"] },
  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: ["fathom"], toolNames: ["fathom_calls_list", "fathom_call_get", "fathom_call_transcript"] },
  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: ["fathom"], toolNames: ["fathom_calls_list", "fathom_call_get", "fathom_call_transcript"] },
  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/fathom",
    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 agent to start using Fathom.

Search & recall

Copy the prompt

Copied

List all calls recorded this week.

Copy the prompt

Copied

Find calls with [person name].

Copy the prompt

Copied

Get the transcript from [call name].

Copy the prompt

Copied

Which calls had [topic] discussed?

Summaries & actions

Copy the prompt

Copied

Summarize my last 5 sales calls.

Copy the prompt

Copied

Get action items from [call name].

Copy the prompt

Copied

Which action items are still open from this week?

Copy the prompt

Copied

What were the key decisions in [call name]?

Coaching & reporting

Copy the prompt

Copied

Which calls lasted over 60 minutes?

Copy the prompt

Copied

Find calls where pricing came up.

Copy the prompt

Copied

List all calls with [account name] this month.

Copy the prompt

Copied

Summarize what was discussed with [company].

SEE HOW AUTH WORKS

Users authorize Fathom once. Their credentials stay vaulted, every call is checked, and every action is logged.

Authorize

Your user connects

Fathom

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

Store

Their

Fathom

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

Resolve

When your agent calls a

Fathom

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

Audit

Every

Fathom

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 meeting intelligence agents and MCP connectors. Working code, live demos, fork what fits.

GTM and RevOps Teams

CRM AI agent

Reads the Granola transcript after every call, extracts next steps and updates the HubSpot record, drafts the follow-up in Gmail, and confirms in Slack, all on the rep's own delegated OAuth.

GTM and RevOps Teams

Sales call prep agent

Reads tomorrow's calls from Google Calendar, mines past Granola notes and Attio history for context, and delivers each rep a prep brief in Slack, scoped to the calls that rep actually owns.

GTM and RevOps Teams

Deal intelligence agent

Pulls recent Gong calls, scores deal risk with an LLM, cross-references the record in Attio, and DMs each owner their at-risk deals in Slack. Every read is scoped to that rep's own access.

GTM and RevOps Teams

Competitive intelligence briefing agent

Scans Gong calls for competitor mentions, matches each one to its Notion battlecard, and DMs every affected rep a single Slack digest per cycle. Every call runs as the PMM who owns the briefing, never a shared bot.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

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.

Fathom 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 Fathom as the user or as a shared key?

As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Fathom bearer token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Fathom?

Yes. Pass a tool name filter to listScopedTools so the meeting intelligence agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Fathom.

What happens when a user revokes Fathom access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Can the agent surface recordings from other reps in the workspace?

Only recordings the authorizing user can see in Fathom. Personal recordings stay per-user. Shared recordings appear only if explicitly shared with the authorizing user in the workspace.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit