Airtable · Productivity
AIRTABLE_CREATE_RECORD
Create one record in an Airtable table. Use only after explicit user approval. Returns { id, createdTime, fields }.
- Provider
- Airtable
- Access
- Write
- Category
- Productivity
- Version
- v1
Input schema
{
"type": "object",
"properties": {
"baseId": {
"type": "string",
"description": "Airtable base ID (app…)."
},
"tableId": {
"type": "string",
"description": "Airtable table ID (tbl…)."
},
"fields": {
"type": "object",
"description": "Field name → value map for the new record."
}
},
"required": [
"baseId",
"tableId",
"fields"
],
"additionalProperties": false
}How to call it
Expose this tool to any MCP-capable agent (Claude, GPT, or your own) through CybrLink's MCP server. The agent calls airtable_create_record with arguments matching the schema above.
CybrLink validates the input, injects the connected Airtable credentials server-side, and runs a single scoped provider API call through the shared proxy — the same guarded path as the generic call_api tool. The raw secret never reaches the model, and the response is trimmed to just the fields the agent needs.
Write action — gate behind explicit user approval and write scope.
Frequently asked
- How do I let an AI agent airtable create record?
- Connect Airtable to CybrLink, then expose the `airtable_create_record` tool to any MCP-capable agent (Claude, GPT, or a custom framework). The agent calls it with typed arguments; CybrLink injects the Airtable credential server-side and runs one scoped API call. Create one record in an Airtable table. Use only after explicit user approval. Returns { id, createdTime, fields }.
- Does the AI model see my Airtable credentials when using AIRTABLE_CREATE_RECORD?
- No. CybrLink stores the credential in a token vault and injects it on the server for each call, so the model can take this action in Airtable without the OAuth token or API key ever entering its context.