How is this different from connecting Granola MCP directly?

Connected directly, an agent sees every tool the server exposes and holds the credential itself. Through TrustGate you choose which tools each agent gets, and every call is logged against the agent that made it.

What if the Granola MCP API changes?

We track the Granola MCP schema, so the tool catalogue stays current. Tools you have already allowed keep working, and anything new stays denied until you enable it.

Can I give different agents different Granola tools?

Yes. Access is set per agent: one can get a handful of read tools, another the full set. You grant the whole MCP or single tools within it.

Where can I see what my agents did in Granola?

Every call is logged against the agent that made it, with the tool it used. Activity can be sent on to your own monitoring.

Do I need to run the Granola MCP server myself?

No. TrustGate connects to the Granola MCP server and sits in front of it. Your agent only talks to your TrustGate URL, never to Granola directly.

Connect Granola MCP to your AI agents, securely.

Q: Is Granola MCP secure?

The server itself exposes 9 tools, and some of them can write to your Granola account. Behind TrustGate an agent only sees the tools you allow, requests and responses are inspected, and every call is logged. Anything outside the allowlist is denied before it reaches Granola.

One secured endpoint for every Granola call your AI agents make, scoped per user, inspected, and logged.

Get started for free

Get a demo

Try Granola MCP now

What your agents can ask once Granola MCP is connected.

Select the tools your AI agents can call

9 tools from the Granola MCP schema.

Showing 9 tools

query_granola_meetingsreadAnswers natural-language questions about the user's meetings, returning a generated answer with meeting references.
list_meetingsreadLists the meeting notes the user can access, with title, date and attendees.
get_meetingsreadReads meeting notes, including private notes and AI-enhanced summarised notes.
get_meeting_attachmentreadView screenshots of screens shared during a meeting, such as slides, charts, or code.
get_meeting_transcriptreadReads a meeting's raw transcript. Not available on every Granola account.
list_meeting_foldersreadLists the folders the user can access, for scoping a search to a team or project.
get_account_inforeadReturns the email and active workspace of the connected Granola account.
switch_workspacewriteOnly available if you belong to more than one workspace — Change your active Granola workspace. This also changes it in the Granola app and in any other AI tools connected to your account.
sign_outwriteSign this AI tool out of your Granola account. To use a different account, reconnect Granola afterwards.

What Granola MCP exposes

Granola MCP groups its 9 tools into 3 categories, each with a suggested starting policy.

All 9 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Meetings	Natural-language queries over meetings, listing notes and reading their content	Read	Notes can hold private notes as well as shared ones; restrict access
Transcripts	Raw meeting transcripts with speaker labels	Read	Transcripts are governed by a separate workspace switch and are off for some accounts
Organization	Folders the user can access and the connected account	Read / Write	MCP follows the active Granola workspace

Connect Granola MCP to your AI agent

Four steps, under ten minutes.

01
Sign in to NeuralTrust
Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.
02
Choose your agent
When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.
03
Connect Granola
Find Granola in the tool list and connect it.
04
Connect your agent
Follow the steps on screen to add the config to your agent, then send the test prompt.

Permissions down to the single tool

You do not allow Granola MCP or block it. You allow the exact tools each agent can call, one by one.

Granola MCP	9 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 9 tools

Tool by toolConnecting the server is not the unit of access. Each tool is granted on its own.
Default denyA tool you have not enabled is never exposed to the agent.
Approval on writesTools that change or delete things can require a human to confirm.

Is Granola MCP secure?

One endpoint instead of raw credentials. Every call is checked against policy and logged.

AI agentsConnect through your MCP client configuration.	NeuralTrustApply controls based on your configuration.	Granola MCP9 documented tools.
Coding assistants	Connection & credentialsper user	Meetings4 tools
Internal copilots	Tool access policiesdeny by default	Organization4 tools
Workflow automations	Request & response inspectioninline	Transcripts1 tool
Compatible MCP clients	Activity monitoringalerts and logs