Tools
Airtable
List your Airtable bases, read rows with a filter formula, and create or upsert records in batches, from Claude or ChatGPT through Tulina's MCP server.
Official site: airtable.com
What it does
- List reachable bases, and read their tables, fields, types and views
- Read rows with an Airtable filter formula
- Create, update and upsert records in batches
- Read and post comments on a record
A personal access token needs two settings, not one — the scopes, and then each base explicitly granted to it. A token with every scope and no base granted answers 200 with an empty list rather than an error, which is the failure that looks like an empty table. Worth testing the connection before building anything on top of it.
Does Airtable have an MCP server?
Yes, and it is reached here through Tulina's own MCP server rather than a separate one per assistant, in Claude or ChatGPT alike. List the bases a token can reach, read a table's fields and views, pull rows with an Airtable filter formula, create, update or upsert records in batches, or read and post comments on a record, all from the same conversation as the rest of your stack.
Why through Tulina
Most systems now publish their own way for a model to reach them, and that is a good thing — it is what Tulina connects to. The connection was never the hard part. Deciding who may use it, what it is allowed to return, and what the model knows before it asks: that is.
The keys stay in one place
Connect Airtable 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 is handed more access than they need. Revoke it once and everything running on it stops.
What leaves is filtered before it leaves
Roles decide who can reach Airtable at all. Beyond that, a policy on the connector itself decides what comes back: fields dropped, identifiers masked or hashed, people pseudonymised. The data is minimised at the source rather than after it has already reached a model.
Every call is on the record
Runs are logged for the organisation — what was called, by whom, when. That is what makes an automated action reviewable after the fact, and what a security review asks for first.
The run starts knowing your company
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 Airtable returns something usable instead of something generic.
Processes that run on Airtable
None published yet.