AI agents use update_field to create or update resources in Airtable MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Airtable MCP environment.
This tool modifies field properties in Airtable, which is a write operation. It changes metadata reversibly (field definitions can be edited again), so it does not qualify as Destructive. The severity is medium because modifying field properties could affect data integrity or application logic depending on how fields are reconfigured, but the action is undoable.
From the tool's definition Tool name 'update_field' and description 'Update field properties' indicate modification of schema/metadata.
Documented attack patterns abuse exactly the kind of access update_field gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Airtable MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for update_field:
{
"version": "1",
"default": "deny",
"tools": {
"update_field": {
"limits": [
{
"counter": "update_field_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_field stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Update field properties. It is categorised as a Write tool in the Airtable MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Airtable MCP server in PolicyLayer and add a rule for update_field: 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 Airtable MCP. Nothing to install.
update_field 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 update_field 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 update_field. 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.
update_field is provided by the Airtable MCP server (rashidazarang/airtable-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 45 Airtable MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
45 Airtable MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.