# Granola MCP Server: Governed AI Access

Granola's MCP server includes 4 different actions available to any connected model or AI agent. When registered with Barndoor, you can ensure centralized governance, visibility, and control across every AI agent your team uses.

## Tools Available
| Action | Type | Description |
| --- | --- | --- |
| query_granola_meetings | read | Semantic search across Granola meetings with optional date filters. |
| get_meetings | read | Fetches structured meeting data for specific meeting IDs. |
| get_meeting_transcript | read | Returns transcript content for a single meeting. |
| list_meetings | read | Lists meetings visible to the authenticated user. |

## Use cases for Granola
- **Meeting Search**: "Semantic search across meetings", "Find meetings by topic and content", "Filter meeting results by date range"
- **Transcript Access**: "Retrieve full meeting transcripts", "Access verbatim conversation records", "Read meeting dialogue history"
- **Meeting Discovery**: "List all accessible meetings", "Browse meeting history", "Discover past conversations"
- **Meeting Details**: "Get structured meeting data by ID", "Access meeting notes and summaries", "Retrieve detailed meeting information"

## What are the risks of using the Granola MCP without an AI gateway?
- **Uncontrolled reads** — AI agents can pull data out of Granola with no visibility into what was accessed.
- **Ungoverned writes** — agents can create or modify records in Granola with no approval step.
- **Destructive actions** — agents can delete or overwrite Granola data with no approval gate or audit trail.
- **Native OAuth is all-or-nothing** — connecting directly grants an agent everything your user account can do in Granola, with no per-tool scoping.

## Why connect Granola with the Barndoor AI gateway?
Barndoor MCP Governance is the gateway between your AI agents and the tools they use.

| At a glance | Available? |
| --- | --- |
| Fine-grained access controls policies per agent, team, role, user, MCP server and tool call | Yes |
| Approval required before write/destructive actions | Yes (configurable per role) |
| Full audit log (reads and writes) | Yes |
| Sensitive data detection before it reaches a model or agent | Yes |
| Instant access revocation | Yes |
| SOC 2 Type II compliant | Yes |

- **Centralized MCP management** — One place to manage and control every MCP server across the organization.
- **Universal connection** — One universal URL works across every AI provider your team uses.
- **Fine-grained access controls** — Set access policies based on human identities, agent profiles, tool-access, context, and data fields.
- **Protect sensitive data** — Using PII detection, masking, tokenization, and redaction.
- **Observability** — Real-time reporting and dashboards for visibility into what AI is doing with Granola.
- **Enterprise-grade security** — Stay compliant with audit trails and logging.

## Getting started with Granola in Barndoor
1. Connect the Granola MCP server once
2. Define your policies
3. Go live across every AI client

## Frequently asked questions
- **What is MCP?**  
MCP (Model Context Protocol) is an open standard that lets AI models and agents connect to external tools and data sources through a common interface.

- **Is Barndoor secure?**  
Yes, Barndoor is SOC 2 Type II compliant, enforcing fine-grained access control and audit logging.

- **How are Granola schema changes handled?**  
Barndoor tracks tool and schema changes, inheriting deny-by-default access until reviewed and approved.

- **Can I deploy custom-built MCP servers?**  
Yes, Barndoor supports customer-built MCPs, applying the same policy enforcement and audit trail.