Build an MCP server with Airtable
Configured with Agent, Airtable Tool, Chat Trigger, OpenAI Chat Model, and additional nodes. Review the connections and setup before adapting this template.
Node categories in this workflow
- Trigger
- AI & models
- Data store
- Integration
Icons describe general node roles, inferred from node types. Inspect the parameters for the configured action.
Drag to pan; use + and − to zoom. Reconstructed from the exported node positions; nothing runs here. Dashed lines represent non-main connections. Full node names and notes appear below.
How it works
The exported workflow contains the following configured nodes. Their connections are shown above; inspect the JSON for the complete logic, expressions, and external actions.
| Node | Category | Type | Operation |
|---|---|---|---|
| When chat message received | Trigger | Chat Trigger | See node parameters |
| AI Agent | AI & models | Agent | See node parameters |
| Simple Memory | Data store | Memory Buffer Window | See node parameters |
| Airtable MCP Client | Integration | Mcp Client Tool | See node parameters |
| OpenAI Chat Model | AI & models | OpenAI Chat Model | See node parameters |
| MCP Server Trigger | Trigger | Mcp Trigger | See node parameters |
| Get | Data store | Airtable Tool | See node parameters |
| Search | Data store | Airtable Tool | search |
| Update | Data store | Airtable Tool | update |
| Delete | Data store | Airtable Tool | deleteRecord |
| Create | Data store | Airtable Tool | create |
Setup
- Download the JSON and import it into an isolated n8n instance. Leave the workflow inactive.
- Connect your own credentials through n8n’s credential store. Replace
REPLACE_WITH_*values with your resource identifiers. - Inspect API destinations, Code nodes, database queries, file paths, and outbound actions.
- Run with synthetic data and harmless destinations. Enable triggers only after checking the actual outputs.
Requirements
An n8n instance with the listed node types and compatible versions. Service-connected workflows may require accounts, credentials, or paid APIs.
Credential types declared in the source
airtableTokenApiopenAiApi
Workflow notes
Talk to your Airtable database
Talk to your Airtable database
Point to your SSE endpoint, update your credentials and talk to your Airtable to:
- Get records
- Search records
- Update records
- Delete records
- Create records
and more!
This example showcases basic yet powerful functionality for a table.
Feel free to combine it with other tools, connect a Slack channel as trigger node or another as output to receive the updates for the stakeholders and project owners.
Enjoy!
Aitor 1 Node
Build an MCP server with Airtable
Build an MCP server with Airtable
Purpose and structure
This folder contains the Build an MCP server with Airtable workflow. Its executable nodes use agent, airtableTool, chatTrigger, lmChatOpenAi, mcpClientTool, mcpTrigger, memoryBufferWindow. The table and connection map below are derived from the JSON, not an inferred guarantee of behavior.
Setup
Import inactive. Configure your own credentials and replace REPLACE_WITH_* values. Review external destinations and Code nodes before running.
Entry points
When chat message received, MCP Server Trigger
Verification
Sanitized source candidate; not runtime-tested. This overview is generated from node metadata. Read the folder README for the connection map, credential types, and license.
Attribution
https://github.com/Zie619/n8n-workflows/blob/94007c1445d9258a7da116646b79473e7c7c3282/workflows/Stickynote/1899_Stickynote_Airtabletool_Create_Triggered.json MIT; preserve source notices.
Canvas section labels
These name areas of the original canvas; they do not include explanatory instructions.
- Update SSE endpoint