Circleback MCP Server
Connect Circleback to your AI agents with the Circleback MCP server.
Updated
What is Circleback MCP?
The Circleback MCP server is a Model Context Protocol server that connects Circleback to AI agents and assistants as a set of tools. With it connected, an agent can work with Circleback (ai meeting notes — summaries, action items, and automated follow-ups) directly — instead of you copying data in and out by hand.
It is a remote MCP server that uses OAuth, so you point your client at the server URL, authorize once, and the Circleback tools become available to the model.
Connect the Circleback MCP server
Connect Circleback MCP to Claude Code
- 1
Add the server
Use `claude mcp add` with the Circleback MCP server URL (or its `npx` command), following the official docs.
- 2
Authorize
Complete authentication (OAuth) so Claude Code can call the server.
- 3
Verify
Ask Claude to use a Circleback tool to confirm the connection is live.
Connect Circleback MCP to Cursor
- 1
Open MCP settings
In Cursor, go to Settings → MCP → Add new server.
- 2
Add Circleback
Provide the Circleback MCP server URL or command and complete authentication.
- 3
Test
Reference Circleback from chat to confirm Cursor can reach the tools.
Sample use cases
A sales rep needs meeting notes sent to the CRM automatically
Circleback captures the call, generates a summary with action items, and the agent pushes the notes and next steps into the CRM deal record.
A project manager tracks action items across all team meetings
The agent collects Circleback action items from the past week, groups them by assignee, and posts an accountability digest to the team channel.
A founder reviews investor meeting takeaways before follow-ups
It pulls Circleback summaries tagged 'investor,' extracts key concerns and commitments, and drafts personalized follow-up emails.
A hiring manager consolidates interview feedback
The agent retrieves Circleback notes from all interviewers for a candidate, merges scorecards, and flags conflicting assessments for discussion.
A customer success manager prepares for quarterly business reviews
It searches past Circleback meetings with the account, pulls recurring themes and open action items, and builds a QBR prep doc.
A team lead runs a decision-log audit at the end of each quarter
The agent extracts all decisions from Circleback meeting notes, timestamps them, and compiles a searchable decision register.
An executive assistant distributes meeting summaries to stakeholders
After each leadership meeting, the agent formats the Circleback summary and emails it to attendees and their direct reports within 10 minutes.
Using Circleback MCP with Gamut
On Gamut, the Circleback MCP server becomes a tool your agents use inside an automated, event-driven workflow — triggered by an event or a schedule, acting through Circleback and your other connected MCP servers, with the connection managed by Gamut rather than a local config file.
Frequently asked questions
What is the Circleback MCP server?
It is a Model Context Protocol server that exposes Circleback to AI agents as tools so they can work with it (ai meeting notes — summaries, action items, and automated follow-ups).
How do I connect the Circleback MCP server?
Point your MCP client (Claude, Cursor, or Gamut) at the Circleback MCP server URL and complete authentication (OAuth). See the official documentation for the exact URL and scopes.
Can I use Circleback MCP with Gamut?
Yes — Gamut supports the Circleback MCP server, so your agents can use it as a tool in automated, triggered workflows.
Which video platforms does Circleback support?
Circleback works with Zoom, Google Meet, and Microsoft Teams. It joins meetings as a bot or uses calendar integrations to record automatically.
How accurate are Circleback's AI-generated notes?
Circleback uses large language models to summarize meetings and extract action items. Accuracy is high for English-language calls, though users should review notes for nuance in complex discussions.
Does Circleback store my meeting recordings?
Circleback stores transcripts and AI-generated notes. Recording storage depends on your plan — some tiers include video/audio retention while others keep only the text artifacts.
How does the Circleback MCP server work with AI agents?
The MCP server exposes meeting notes, action items, and transcripts as standardized tools, so AI agents can search past meetings and extract insights without manual exports.