Baserow MCP integration for AI agents.

Connect AI agents to Baserow through 7 structured actions, including get table row, create table row, and delete table row. Review authentication, inputs, wo…

ACTION CONTRACTS
7
AUTHENTICATION
API key
SOURCE STATUS
Provider-backed

CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE

CAPABILITY PROFILE

What the Baserow integration exposes

The Baserow Agent App exposes 7 provider-backed actions for productivity and data work. Its current contract lets an authorized agent read one baserow row by table id and row id, create one row in a baserow table, and delete one baserow row by row id. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.

A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.

For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected Baserow account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.

VERIFIED ACTION SAMPLE

Real Baserow capabilities.

Showing 7 of 7 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.

get_table_rowREAD

Read one Baserow row by table ID and row ID.

INPUTS: tableId / rowId / userFieldNames

create_table_rowWRITE

Create one row in a Baserow table.

INPUTS: tableId / userFieldNames / row

delete_table_rowHIGH IMPACT

Delete one Baserow row by row ID.

INPUTS: tableId / rowId

list_table_fieldsREAD

List the field definitions for one Baserow table.

INPUTS: tableId

list_table_rowsREAD

List rows from one Baserow table with optional search, ordering, filters, and pagination.

INPUTS: tableId / userFieldNames / search / orderBy / filters

list_tablesREAD

List the Baserow tables accessible to the authenticated database token.

update_table_rowWRITE

Update one existing Baserow row.

INPUTS: tableId / rowId / userFieldNames / row

INPUT CONTRACTS

Know what the action needs before it runs.

get_table_row

tableIdREQUIRED
The Baserow table ID.
rowIdREQUIRED
The Baserow row ID.
userFieldNamesOPTIONAL
Whether Baserow should use user-facing field names instead of field IDs.

create_table_row

tableIdREQUIRED
The Baserow table ID.
userFieldNamesOPTIONAL
Whether Baserow should use user-facing field names instead of field IDs.
rowREQUIRED
A Baserow row payload keyed by field name or field ID.

delete_table_row

tableIdOPTIONAL
The Baserow table ID.
rowIdOPTIONAL
The Baserow row ID.

list_table_fields

tableIdOPTIONAL
The Baserow table ID.

PROVIDER-SPECIFIC WORKFLOWS

Jobs this Agent App can support

Inspect Get Table Row

Read one Baserow row by table ID and row ID. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.

get_table_row

Control Create Table Row

Create one row in a Baserow table. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.

create_table_row

Verify with List Table Fields

List the field definitions for one Baserow table. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.

list_table_fields

SAFETY BOUNDARY

Operate Baserow with explicit limits

  • Authorize Baserow with API key and grant only the provider access required by the selected actions.
  • 3 actions are change-capable by name. Confirm the target identity and material parameters before allowing a write.
  • Treat `delete_table_row` as high-impact operations and require an explicit approval boundary.
  • No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in Baserow rather than assuming unrestricted access.
  • After a call, inspect the structured result and execution record before reporting that the Baserow task completed successfully.

CONNECTION MODEL

API key

Baserow database token used with the Authorization Token header. Create it in Workspace settings > Database tokens: https://baserow.io/user-docs/personal-api-tokens.

Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.

READ SIGNALS
4
WRITE SIGNALS
2
HIGH IMPACT
1
REVIEW SIGNALS
0

EVIDENCE AND AVAILABILITY

Provider reference

Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by Baserow.

Official Baserow website

ONE CONNECTION. REAL WORK.

Give your agent software it can use.

Connect through MCP or explore the Agent App catalog and choose only the capabilities your workflow needs.

EXPLORE AGENT APPS