Create or update multiple records in a single operation
AI agents use batch_upsert to create or update resources in MCP Airtable Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Airtable Server environment.
This tool modifies data (creates or updates records) but does not delete or destroy data irreversibly. The batch nature and potential to affect multiple records elevates severity from low to medium, as an AI agent could inadvertently overwrite significant amounts of data if given incorrect arguments.
From the tool's definition Tool description explicitly states 'Create or update multiple records in a single operation'. The verb 'upsert' (update or insert) combined with 'batch' and 'multiple records' indicates reversible modifications to data.
Attacks that exploit this kind of access
Create or update multiple records in a single operation. It is categorised as a Write tool in the MCP Airtable Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Airtable Server MCP server in PolicyLayer and add a rule for batch_upsert: 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 MCP Airtable Server. Nothing to install.
batch_upsert 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 batch_upsert 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 batch_upsert. 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.
batch_upsert is provided by the MCP Airtable Server MCP server (marchi-lau/mcp-airtable). 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 →