AI agents use airtable_action to create or update resources in UnClick — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your UnClick environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
view | string | — | View name or ID to use. |
action | string | Yes | Action: list_bases, list_records, get_record, create_record, update_record, search_records. |
fields | object | — | Record fields as key-value pairs (for create_record and update_record). |
offset | string | — | Pagination offset token. |
base_id | string | — | Airtable base ID (starts with 'app'). |
formula | string | — | Airtable filter formula string (for search_records). |
page_size | number | — | Number of records per page (max 100). |
record_id | string | — | Record ID (starts with 'rec'). |
table_name | string | — | Table name or ID. |
max_records | number | — | Maximum number of records to return. |
access_token | string | Yes | Airtable personal access token (PAT). |
Parameters from the server's own tool schema.
The tool's primary risk comes from its ability to create and modify data in Airtable bases. An AI agent with access could create unwanted records or corrupt existing data, though such changes are reversible (records can be deleted or edited by authorized users). The blast radius is limited to data within connected Airtable workspaces.
From the tool's definition Description states the tool can 'create or update records' in Airtable via REST API. While it also includes read operations ('list bases', 'list and search records', 'get a single record'), the presence of write capabilities (create/update) makes this a…
Risk signalsHandles credentials or secrets (access_token) · High parameter count (11 properties)
Attacks that exploit this kind of access
Interact with the Airtable REST API: list bases, list and search records, get a single record, and create or update records. It is categorised as a Write tool in the UnClick MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
airtable_action accepts 11 parameters: view, action, fields, offset, base_id, formula, page_size, record_id, table_name, max_records, access_token. Required: action, access_token. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for airtable_action: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches UnClick. Nothing to install.
airtable_action is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the airtable_action rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for airtable_action. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
airtable_action is provided by the UnClick MCP server (@unclick/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →