ToolsConnector
Grain
List and read meeting recordings with AI summaries and highlights, or pull a full transcript, from Claude or ChatGPT, through Tulina's MCP server.
Official site: grain.com
What it can do
3 read/1 write
- 01Read
List and read recordings, with the AI summary and highlights
- 02Read
Read a full transcript as text, VTT or SRT
- 03Write
Tag, rename or share a recording with a person or a team
- 04Read
Subscribe to new recordings through a webhook
A personal access token is not a personal scope. Listing recordings without a filter returns every workspace-visible recording in the organization — colleagues' calls the token holder never attended, sorted newest first — which is Grain's documented behavior, not a bug. Asking for your own meetings means saying so: filter on attendance, or read someone else's week by accident.
How do you connect Grain to Claude and ChatGPT?
Through Tulina's own MCP server, not Grain's own hosted one. List and read meeting recordings with their AI summary and highlights, pull a full transcript as text, VTT or SRT, or tag, rename and share a recording with a person or team, in the same chat as the deal or account review it feeds, whether that chat is Claude or ChatGPT.
Why through Tulina
The connection was never the hard part.
Most systems now publish their own way for a model to reach them, and that is good: it is what Tulina connects to. The hard part is deciding who may use it, what it is allowed to return, and what the model knows before it asks.
The keys stay in one place
YouTeamOrganisation
Connect Grain once. The credential is encrypted in a vault, never held in clear, and never pasted into a chat or a workflow file. A person uses their own key where they have one, their team's where they do not, the organisation's after that, so nobody is blocked and nobody holds more access than they need. Revoke it once and everything running on it stops.
What leaves is filtered before it leaves
fields droppedmasked or hashedpseudonymised
Roles decide who can reach Grain at all. Beyond that, a policy on the connector itself decides what comes back. The data is minimised at the source rather than after it has already reached a model.
Every call is on the record
whatwhowhen
Runs are logged for the organisation. That is what makes an automated action reviewable after the fact, and it is what a security review asks for first.
The run starts knowing your company
namingkey accountsdecisions
A direct connection gives a model access. It does not tell it how your company names things, which accounts matter, or what was decided last quarter. Tulina carries that across every tool, so the same request against Grain returns something usable instead of something generic.
Processes that run on Grain
None published yet.