# Circleback MCP

```json
{
  "name": "Circleback MCP",
  "slug": "circleback_mcp",
  "url": "https://composio.dev/toolkits/circleback_mcp",
  "markdown_url": "https://composio.dev/toolkits/circleback_mcp.md",
  "logo_url": "https://logos.composio.dev/api/circleback_mcp",
  "categories": [
    "productivity & project management"
  ],
  "is_composio_managed": false,
  "updated_at": "2026-10-04T17:27:41.738Z"
}
```

![Circleback MCP logo](https://logos.composio.dev/api/circleback_mcp)

## Description

Securely connect your AI agents and chatbots (Claude, ChatGPT, Cursor, etc) with Circleback MCP or direct API to search meetings, fetch transcripts, extract action items, and surface related contacts through natural language.

## Summary

Circleback MCP is a platform that indexes meetings, transcripts, action items, calendar events, emails, people, companies, and support documentation.
Use it to quickly find context across meetings and team knowledge.

## Categories

- productivity & project management

## Toolkit Details

- Tools: 11

## Images

- Logo: https://logos.composio.dev/api/circleback_mcp

## Authentication

- **Dcr Oauth**
  - Type: `custom`
  - Description: Dcr Oauth authentication for Circleback MCP.
  - Setup:
    - Configure Dcr Oauth credentials for Circleback MCP.
    - Use the credentials when creating an auth config in Composio.

## Suggested Prompts

- Summarize meeting transcripts from last week
- Find action items assigned to me today
- List calendar conflicts across my meetings

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `CIRCLEBACK_MCP_FIND_COMPANIES` | Findcompanies | Find companies matching the given search terms. Searches match company names and company domains. The data returned will be an array of objects with each company's domain and name when available. |
| `CIRCLEBACK_MCP_FIND_PROFILES` | Findprofiles | Find profiles matching the given names. The data returned will be an array of objects representing each of the matching profiles. |
| `CIRCLEBACK_MCP_GET_TRANSCRIPTS_FOR_MEETINGS` | Gettranscriptsformeetings | Get the full transcripts for given meeting IDs. Use string IDs like Vd6Pz_kWqLm3xY-c8RhTn. The data returned will be an array of objects, each representing a full transcript for a meeting. Each transcript object will contain the meetingId, meetingName, and an array of transcript segments. Each segment is formatted with timestamps like: {startTimestamp: 123.45, endTimestamp: 128.00, speaker: 'John Doe', words: 'This is a test.'} This should be used to get detailed transcript information for one or many meetings at once. |
| `CIRCLEBACK_MCP_LIST_TAGS` | Listtags | List all tags available in the user's workspace. Returns an array of tag objects with their IDs and names. Use this to discover available tags before filtering meetings, transcripts, or action items by tag. |
| `CIRCLEBACK_MCP_READ_MEETINGS` | Readmeetings | Given up to 50 meeting IDs, fetch detailed information for each meeting. Use string IDs like Vd6Pz_kWqLm3xY-c8RhTn. The data returned will be an array of objects, with each containing the meeting ID, name, notes, attendees, action items, AI-generated insights, creator, tags, status, duration, and creation date. |
| `CIRCLEBACK_MCP_SEARCH_ACTION_ITEMS` | Searchactionitems | Find action items that match a given search term or filter. Returns action items with their title, description, status, assignee, and related meeting details. By default, only action items assigned to the user are returned. To find action items assigned to someone else, use FindProfiles to resolve their name to a profile ID and pass it as assigneeProfileId. Action items can be filtered by search terms, status (PENDING or DONE), tags, and meeting date range (startDate/endDate). Only 25 action items are returned per page, so this function may need to be called multiple times if there are more than that many results. If 25 action items are returned, call this function again with the next pageIndex to ensure you get all results. |
| `CIRCLEBACK_MCP_SEARCH_CALENDAR_EVENTS` | Searchcalendarevents | Get calendar events from the user's connected calendars. When searching for calendar events, the tool will extract relevant excerpts based on the intent instead of returning the entire data. Each calendar event excerpt includes comprehensive details: event title, date (in the user's timezone), organizer email, attendees (with names, emails, and status), calendar description (if present), meeting platform (Zoom, Google Meet, Microsoft Teams, etc.), meeting platform link, whether it's a recurring event, Circleback join status, and any associated meeting data from the Circleback (meeting ID, status, tag IDs, user notes). You can filter events by providing a date range using startDate and endDate parameters. This is useful for finding upcoming meetings, scheduled calls, or calendar events that the user has. Note: This should be primarily used for searching calendar events happening in the future. Past calendar events have a meeting record if they were captured with Circleback. The only reason to use this to search past calendar events is if searching for the meeting with SearchMeetings yielded no relevant results. Only 50 calendar events are returned per page, so this function may need to be called multiple times if there are more than that many results. If 50 events are returned, call this function again with the next pageIndex to ensure you get all results. |
| `CIRCLEBACK_MCP_SEARCH_EMAILS` | Searchemails | Search the user's connected email accounts for email threads matching a query. This should be used when the user asks questions about their emails or needs to find specific email conversations. This function queries across all connected email services and retrieves up to 20 matching email threads per service per page. The data returned will be an array of objects, with each containing the email thread ID, subject line, and relevant excerpts. Each email thread object includes metadata such as the sender email, received date, and the fromEmailAddress of the connected account the thread belongs to (if available). Only 20 email threads are returned per page, so this function may need to be called multiple times if there are more than that many results. |
| `CIRCLEBACK_MCP_SEARCH_MEETINGS` | Searchmeetings | Find meetings that match a given search term or filter. Searches can be done by direct match on the meeting name or notes. Search term is a direct match ignoring case, prefer to search for a single word or phrase if provided. Searches can also be performed for tags or related profiles (attendees of the meetings). When searching for a meeting, the tool will find the appropriate meeting and extract the relevant source excerpt based on the intent instead of returning the entire data. NOTE: A search term is not explicitly required, for example if you want to find all meetings with a specific tag in a date range, only include those and don't pass a searchTerm. To restrict the search further, you can provide a start and end date. This will significantly improve performance. The data returned will be an an array of objects, with each containing meeting data. Only 20 meetings are returned per page, so this function may need to be called multiple times if there are more than that many results. If 20 meetings are returned, call this function again with the next pageIndex to ensure you get all results. IMPORTANT: The pageIndex is only valid for the exact same search parameters (aside from pageIndex). For example, if you provide a start / end date to fetch page 0, then you must provide the EXACT SAME start / end dates to fetch page 1. |
| `CIRCLEBACK_MCP_SEARCH_SUPPORT_ARTICLES` | Searchsupportarticles | Search for support articles about Circleback to find relevant documentation and help content. |
| `CIRCLEBACK_MCP_SEARCH_TRANSCRIPTS` | Searchtranscripts | Search meeting transcripts to find transcript chunks that match a given search term. If the user's question requires searching for multiple distinct search terms, you should call this function multiple times. The data returned will be an an array of objects, with each containing the meeting ID, name, creator user ID, when it was created, the chunk matching the search term, and the start and end timestamps of the matching chunk. Search results can be further filtered by including tags, profiles (attendees), or domains. This function is useful to find relevant meetings where a search term was mentioned. We can find more details about those meetings using the ReadMeetings tool. |

## Supported Triggers

None listed.

## Installation and MCP Setup

### Path 1: SDK Installation

#### Path 1, Step 1: Install Composio

Install the Composio SDK, the OpenAI provider, and the OpenAI SDK
```python
pip install composio composio_openai openai
```

```typescript
npm install @composio/core @composio/openai openai
```

#### Path 1, Step 2: Create a Composio session

Initialize Composio with the OpenAI Responses provider and create a session scoped to Circleback MCP
```python
import json
from openai import OpenAI
from composio import Composio
from composio_openai import OpenAIResponsesProvider

composio = Composio(provider=OpenAIResponsesProvider())
client = OpenAI()

session = composio.create(user_id="your-user-id", toolkits=["circleback_mcp"])
tools = session.tools()
```

```typescript
import OpenAI from "openai";
import { Composio } from "@composio/core";
import { OpenAIResponsesProvider } from "@composio/openai";

const composio = new Composio({ provider: new OpenAIResponsesProvider() });
const client = new OpenAI();

const session = await composio.create("your-user-id", { toolkits: ["circleback_mcp"] });
const tools = await session.tools();
```

#### Path 1, Step 3: Run Circleback MCP tools with your agent

Send a request, execute the Circleback MCP tool calls through the session, and print the final answer
```python
response = client.responses.create(
    model="gpt-5.6-sol",
    tools=tools,
    input=[{"role": "user", "content": "Summarize meeting transcripts from last week"}],
)

while True:
    tool_calls = [o for o in response.output if o.type == "function_call"]
    if not tool_calls:
        break
    results = composio.provider.handle_tool_calls(response=response, session=session)
    response = client.responses.create(
        model="gpt-5.6-sol",
        tools=tools,
        previous_response_id=response.id,
        input=[
            {"type": "function_call_output", "call_id": call.call_id, "output": json.dumps(results[i])}
            for i, call in enumerate(tool_calls)
        ],
    )

print(response.output_text)
```

```typescript
let response = await client.responses.create({
  model: "gpt-5.6-sol",
  tools,
  input: [{ role: "user", content: "Summarize meeting transcripts from last week" }],
});

while (response.output.some((o) => o.type === "function_call")) {
  const outputs = await composio.provider.handleToolCalls(session, response.output);
  response = await client.responses.create({
    model: "gpt-5.6-sol",
    tools,
    previous_response_id: response.id,
    input: outputs,
  });
}

console.log(response.output_text);
```

### Path 2: MCP Server Setup

#### Path 2, Step 1: Install Composio

Install the Composio SDK and your agent framework
```python
pip install composio claude-agent-sdk
```

```typescript
npm install @composio/core ai @ai-sdk/mcp @ai-sdk/openai
```

#### Path 2, Step 2: Create a session with MCP enabled

Create a session scoped to Circleback MCP and read its MCP URL and headers
```python
from composio import Composio

composio = Composio()
session = composio.create(user_id="your-user-id", toolkits=["circleback_mcp"], mcp=True)
```

```typescript
import { Composio } from "@composio/core";

const composio = new Composio();
const { mcp } = await composio.create("your-user-id", {
  toolkits: ["circleback_mcp"],
  mcp: true,
});
```

#### Path 2, Step 3: Connect your agent to the MCP server

Pass the session's MCP URL and headers to your agent and run a Circleback MCP request
```python
import asyncio
from claude_agent_sdk import ClaudeSDKClient, ClaudeAgentOptions, AssistantMessage, TextBlock

options = ClaudeAgentOptions(
    mcp_servers={
        "composio": {
            "type": "http",
            "url": session.mcp.url,
            "headers": session.mcp.headers,
        }
    },
    system_prompt="You are a helpful assistant with access to Circleback MCP tools.",
    tools=[],
    allowed_tools=["mcp__composio__*"],
)

async def main():
    async with ClaudeSDKClient(options=options) as client:
        await client.query("Summarize meeting transcripts from last week")
        async for message in client.receive_response():
            if isinstance(message, AssistantMessage):
                for block in message.content:
                    if isinstance(block, TextBlock):
                        print(block.text)

asyncio.run(main())
```

```typescript
import { createMCPClient } from "@ai-sdk/mcp";
import { openai } from "@ai-sdk/openai";
import { generateText, stepCountIs } from "ai";

const client = await createMCPClient({
  transport: { type: "http", url: mcp.url, headers: mcp.headers },
});

const { text } = await generateText({
  model: openai("gpt-5.6-sol"),
  tools: await client.tools(),
  prompt: "Summarize meeting transcripts from last week",
  stopWhen: stepCountIs(10),
});

console.log(text);
await client.close();
```

## Why Use Composio?

### 1. AI Native Circleback MCP Integration

- Supports both Circleback MCP and direct API based integrations
- Structured, LLM-friendly schemas for reliable tool execution
- Rich coverage for reading, writing, and querying your Circleback MCP data

### 2. Managed Auth

- Built-in OAuth handling with automatic token refresh and rotation
- Central place to manage, scope, and revoke Circleback MCP access
- Per user and per environment credentials instead of hard-coded keys

### 3. Agent Optimized Design

- Tools are tuned using real error and success rates to improve reliability over time
- Comprehensive execution logs so you always know what ran, when, and on whose behalf

### 4. Enterprise Grade Security

- Fine-grained RBAC so you control which agents and users can access Circleback MCP
- Scoped, least privilege access to Circleback MCP resources
- Full audit trail of agent actions to support review and compliance

## Use Circleback MCP with any AI Agent Framework

Choose a framework you want to connect Circleback MCP with:

- [ChatGPT](https://composio.dev/toolkits/circleback_mcp/framework/chatgpt)
- [Claude Cowork](https://composio.dev/toolkits/circleback_mcp/framework/claude-cowork)
- [Hermes](https://composio.dev/toolkits/circleback_mcp/framework/hermes-agent)
- [Atomic Agent](https://composio.dev/toolkits/circleback_mcp/framework/atomic-agent)

## Related Toolkits

- [Google Sheets](https://composio.dev/toolkits/googlesheets) - Google Sheets is a cloud-based spreadsheet tool for real-time collaboration and data analysis. It lets teams work together from anywhere, updating information instantly.
- [Notion](https://composio.dev/toolkits/notion) - Notion is a collaborative workspace for notes, docs, wikis, and tasks. It streamlines team knowledge, project tracking, and workflow customization in one place.
- [Airtable](https://composio.dev/toolkits/airtable) - Airtable combines the flexibility of spreadsheets with the power of a database for easy project and data management. Teams use Airtable to organize, track, and collaborate with custom views and automations.
- [Asana](https://composio.dev/toolkits/asana) - Asana is a collaborative work management platform for teams to organize and track projects. It streamlines teamwork, boosts productivity, and keeps everyone aligned on goals.
- [Google Tasks](https://composio.dev/toolkits/googletasks) - Google Tasks is a to-do list and task management tool integrated into Gmail and Google Calendar. It helps you organize, track, and complete tasks across your Google ecosystem.
- [Linear](https://composio.dev/toolkits/linear) - Linear is a modern issue tracking and project planning tool for fast-moving teams. It helps streamline workflows, organize projects, and boost productivity.
- [Jira](https://composio.dev/toolkits/jira) - Jira is Atlassian’s platform for bug tracking, issue tracking, and agile project management. It helps teams organize work, prioritize tasks, and deliver projects efficiently.
- [Clickup](https://composio.dev/toolkits/clickup) - ClickUp is an all-in-one productivity platform for managing tasks, docs, goals, and team collaboration. It streamlines project workflows so teams can work smarter and stay organized in one place.
- [Monday](https://composio.dev/toolkits/monday) - Monday.com is a customizable work management platform for project planning and collaboration. It helps teams organize tasks, automate workflows, and track progress in real time.
- [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time.
- [Agiled](https://composio.dev/toolkits/agiled) - Agiled is an all-in-one business management platform for CRM, projects, and finance. It helps you streamline workflows, consolidate client data, and manage business processes in one place.
- [AirOps MCP](https://composio.dev/toolkits/airops_mcp) - AirOps MCP is AirOps' managed content platform exposing brand context, knowledge bases, and workflows. Use it to give agents brand-aware content, automate content workflows, and track Brand Kit edits.
- [Amazing Marvin](https://composio.dev/toolkits/amazing_marvin) - Amazing Marvin is a personal productivity app for tasks, projects, habits, planning, time tracking, and rewards. It helps you build a flexible workflow that matches how you actually work.
- [AnyDB](https://composio.dev/toolkits/any_db) - AnyDB is a flexible collaborative database platform for organizing records, files, and automated workflows. It helps teams centralize data, collaborate on records, and automate routine tasks.
- [ApptiveGrid](https://composio.dev/toolkits/apptivegrid) - ApptiveGrid is a collaborative no-code database and app platform for spaces, grids, forms, and structured records. It helps teams organize operational data, collect inputs, and build lightweight business apps without custom backend work.
- [Ascora](https://composio.dev/toolkits/ascora) - Ascora is a cloud-based field service management platform for service businesses. It streamlines scheduling, invoicing, and customer operations in one place.
- [Atlassian MCP](https://composio.dev/toolkits/atlassian_mcp) - Atlassian Rovo MCP connects agents to Jira, Jira Service Management, Confluence, Bitbucket, Compass, and Teamwork Graph workflows. It lets teams surface and act on Atlassian data while respecting existing user permissions.
- [Basecamp](https://composio.dev/toolkits/basecamp) - Basecamp is a project management and team collaboration tool by 37signals. It helps teams organize tasks, share files, and communicate efficiently in one place.
- [Beeminder](https://composio.dev/toolkits/beeminder) - Beeminder is an online goal-tracking platform that uses monetary pledges to keep you motivated. Stay accountable and hit your targets with real financial incentives.
- [Boxhero](https://composio.dev/toolkits/boxhero) - Boxhero is a cloud-based inventory management platform for SMBs, offering real-time updates, barcode scanning, and team collaboration. It helps businesses streamline stock tracking and analytics for smarter inventory decisions.

## Frequently Asked Questions

### Do I need my own developer credentials to use Circleback MCP with Composio?

Yes, Circleback MCP requires you to configure your own Dcr Oauth credentials. Once set up, Composio handles secure credential storage and management for you.

### Can I use multiple toolkits together?

Yes! Composio's Tool Router enables agents to use multiple toolkits. [Learn more](https://docs.composio.dev/tool-router/overview).

### Is Composio secure?

Composio is SOC 2 and ISO 27001 compliant with all data encrypted in transit and at rest. [Learn more](https://trust.composio.dev).

### What if the API changes?

Composio maintains and updates all toolkit integrations automatically, so your agents always work with the latest API versions.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)