Circleback connector for AI agents

CALL ANY TOOL

List and read meeting notes, search transcripts, and track or update action items, each call scoped to the authenticated attendee's workspace access.

circleback_meetings_list

List meetings

Fetch a paginated list of meetings for the authenticated user, filtered by date range or participant.

Parameters

Name

Type

Required

Description

start_date

string

Optional

ISO date to list meetings from

end_date

string

Optional

ISO date to list meetings up to

limit

integer

Optional

Max meetings to return (default 25)

circleback_meeting_get

Get meeting

circleback_notes_get

Get meeting notes

circleback_transcript_get

Get transcript

circleback_action_items_list

List action items

circleback_action_item_update

Update action item

circleback_search

Search conversations

Build your Agent

The same per-user auth pattern wires into every agent framework.

import { ScalekitClient } from "@scalekit-sdk/node";
import { ChatOpenAI } from "@langchain/openai";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(process.env.SCALEKIT_ENV_URL, process.env.SCALEKIT_CLIENT_ID, process.env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["circlebackmcp"], toolNames: ["circleback_meetings_list", "circleback_notes_get", "circleback_action_items_list"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm: new ChatOpenAI({ model: "gpt-4o" }), tools });
await agent.invoke({ messages: [{ role: "user", content: "Summarise this week's customer calls" }] });

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

const openai = new OpenAI();
const sk = new ScalekitClient(process.env.SCALEKIT_ENV_URL, process.env.SCALEKIT_CLIENT_ID, process.env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["circlebackmcp"], toolNames: ["circleback_meetings_list", "circleback_notes_get", "circleback_action_items_list"] },
  pageSize: 100,
});

const res = await openai.responses.create({
  model: "gpt-4o",
  input: "List open action items from my calls",
  tools,
});

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

const anthropic = new Anthropic();
const sk = new ScalekitClient(process.env.SCALEKIT_ENV_URL, process.env.SCALEKIT_CLIENT_ID, process.env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["circlebackmcp"], toolNames: ["circleback_meetings_list", "circleback_notes_get", "circleback_action_items_list"] },
  pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6",
  max_tokens: 1024,
  tools,
  messages: [{ role: "user", content: "Pull notes from my Acme call" }],
});

import { LlmAgent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(process.env.SCALEKIT_ENV_URL, process.env.SCALEKIT_CLIENT_ID, process.env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["circlebackmcp"], toolNames: ["circleback_meetings_list", "circleback_notes_get", "circleback_action_items_list"] },
  pageSize: 100,
});

const agent = new LlmAgent({ name: "circleback_agent", model: "gemini-2.0-flash", tools });
await agent.run("What did we agree in yesterday's kickoff?");

Try these prompts

Paste any prompt into your agent to start working with Circleback meetings.

Recap & summarise

Copy the prompt

Copied

Summarise my customer calls from this week.

Copy the prompt

Copied

What were the key decisions in the Acme kickoff?

Copy the prompt

Copied

Give me the notes from yesterday's product sync.

Action items

Copy the prompt

Copied

List my open action items across all meetings.

Copy the prompt

Copied

Mark the pricing follow-up for Acme as done.

Copy the prompt

Copied

Reassign the SOW draft to Priya.

Search & recall

Copy the prompt

Copied

What did the customer say about the security review?

Copy the prompt

Copied

Find every meeting where we discussed renewal terms.

Copy the prompt

Copied

Pull the transcript passage where pricing came up.

SEE HOW AUTH WORKS

The user authorises Circleback once. Every later agent call uses their token with workspace scope enforced.

1

Authorize

Your user connects

Circleback 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

Circleback 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

Circleback 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

Circleback 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

See the same per-user auth pattern across other transcription connectors.

No items found.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Meeting notes and transcripts need real per-user attribution.

01.

Shared tokens break per-user analytics

A shared Circleback token looks fine in a demo. In production every notes read and action-item update logs as one service account, so you lose track of who acted. Scalekit resolves the real attendee's credential per call.

// shared token
update → assistant_bot

// scalekit
update → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Circleback 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 Circleback as the user or as a shared key?

As the user. Scalekit resolves the authenticated attendee's own Circleback credential at request time, so every notes read, transcript pull, and action-item update is attributed to them rather than a shared assistant bot.

Where is the Circleback token stored?

In an AES-256 encrypted vault, namespaced per tenant. Tokens are fetched only at the moment of a tool call, refreshed automatically before expiry, and revocable from a single dashboard, never exposed to the model or the prompt.

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

Yes. Pass a toolNames filter to listScopedTools to expose only the actions you want, for example read-only notes and search without action-item writes. Scalekit also runs a scope check before each API call.

What happens when a user revokes Circleback access?

The credential is invalidated at the next tool call, which fails closed rather than falling back to a shared token. Other users are unaffected, and the revocation is recorded in the audit trail.

Can the agent search across every meeting or only ones I attended?

Only meetings the authenticated user can access. Because the search runs with their own credential, results are limited to their workspace and the conversations they were part of, so nothing leaks across users or tenants.

Circleback MCP

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