1 safety and 1 privacy notes across 2 risk areas. Review closely: credentials & tokens.
2 areas
SafetyCredentials & tokensRestrict the Airtable API key to the bases and write scopes Claude is allowed to use before enabling record or schema changes.
PrivacyGeneralAirtable records, field values, attachments, and base metadata may be sent through the MCP client and model context.
Safety notes
Restrict the Airtable API key to the bases and write scopes Claude is allowed to use before enabling record or schema changes.
Privacy notes
Airtable records, field values, attachments, and base metadata may be sent through the MCP client and model context.
Prerequisites
Node.js 18+ installed for running npx commands and MCP server packages
Airtable Personal Access Token (PAT) from https://airtable.com/account
Read and write records, manage bases and tables in Airtable directly from Claude
Content
Connect Claude to Airtable databases for seamless data management and automation of your bases and tables.
Features
Read and write records in Airtable bases
Create and manage tables with full schema control
Query and filter data with complex conditions
Update multiple records in batch operations
Access metadata and schema information
Advanced Airtable base and table management with automatic schema detection, field type validation, and relationship mapping for complex data structures
Batch operations support for efficient bulk record creation, updates, and deletions with automatic rate limit handling and retry logic
Real-time data synchronization capabilities with webhook integration support for monitoring base changes and triggering automated workflows
Use Cases
Automate data entry and updates across multiple bases
Generate reports from Airtable data with AI analysis
Sync data between Airtable and other systems
Bulk operations on records for data cleaning
Create dynamic dashboards from Airtable content
Build automated data pipelines that sync external data sources with Airtable bases for real-time data management and reporting
Installation
Claude Code
claude mcp add airtable --env AIRTABLE_API_KEY=YOUR_KEY -- npx -y airtable-mcp-server
Ask Claude: "Read all records from the Projects table"
Add a new contact with these details to Airtable
Common usage pattern for this MCP server
Ask Claude: "Add a new contact with these details to Airtable"
Update the status field for all overdue tasks
Common usage pattern for this MCP server
Ask Claude: "Update the status field for all overdue tasks"
Filter records where status='active' AND priority=...
Common usage pattern for this MCP server
Ask Claude: "Filter records where status='active' AND priority='high'"
Query Records with Filtering
Query Airtable records using formula-based filtering to retrieve specific data subsets
// Query Airtable records with formula filtering
const records = await airtable.query({
baseId: "appXXXXXXXXXXXXXX",
table: "Projects",
filterByFormula: "{Status} = 'Active'",
maxRecords: 100,
});
Security
Use read-only API keys when write access isn't needed
Limit access to specific bases when possible
Regularly rotate API keys for security
Monitor API usage through Airtable dashboard
Airtable API tokens and personal access tokens must be securely stored and never exposed in client-side code or public repositories - use environment variables and secure credential management
OAuth access tokens should be used for third-party integrations instead of personal access tokens to ensure proper access control and token lifecycle management
Airtable base IDs and table names may expose data structure and organization information - ensure base IDs are kept private and not shared in public configurations
Rate limiting and API quota management are critical for Airtable MCP servers - implement proper rate limit handling, retry logic, and quota monitoring to prevent service disruption
Airtable webhook configurations and payloads may contain sensitive data - ensure webhook endpoints are properly secured with authentication and HTTPS encryption
Troubleshooting
Authentication failed with 401 Unauthorized error
Verify Personal Access Token at https://airtable.com/account has correct scopes. Ensure token grants access to specific base. Check AIRTABLE_API_KEY environment variable matches your PAT.
Rate limit exceeded - 5 requests per second throttling
Implement 200ms delay between requests (5 req/sec limit). Use batch endpoints to update 10 records per request. Consider batching to achieve 50 updates/second maximum throughput.
Base or table not found with 404 error
Verify base ID starts with 'app' prefix. Check table name is exact case-sensitive match. Confirm PAT has base-level permissions granted at https://airtable.com/account.
Field validation errors when creating or updating records
Match field types exactly (text, number, single select, etc). Provide all required fields. Use GET request to table schema to verify field names, types, and validation rules.
Airtable MCP server authentication errors with personal access tokens
Verify token is valid and not expired. Check token scopes match required permissions. Ensure token format is correct (Bearer token in Authorization header). For OAuth integrations, verify token refresh logic is working correctly.
Rate limit errors when querying large Airtable bases
Implement exponential backoff retry logic with jitter. Use batch operations to reduce API calls. Cache frequently accessed data. Monitor rate limit headers and adjust request frequency accordingly.
Airtable base schema changes breaking MCP server operations
Implement schema validation and versioning. Use Airtable's schema API to detect changes. Add error handling for missing fields or changed field types. Consider using field IDs instead of field names for stability.
Airtable MCP server connection timeouts or network errors
Check network connectivity and firewall settings. Verify Airtable API endpoints are accessible. Increase request timeout values. Implement connection pooling and retry mechanisms with exponential backoff.
Show that Airtable MCP Server for Claude is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/mcp/airtable-mcp-server)
How it compares
Airtable MCP Server for Claude side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
3 trust signals differ across this comparison (Package trust, Source provenance, Submitter).
MCP support in Azure Data API Builder for exposing configured database entities as MCP tools, including entity discovery and DML operations over Azure databases and supported on-premises data stores.
Official LINE MCP server that connects Claude and other AI agents to the LINE Messaging API for push messages, broadcasts, profile lookup, quotas, follower IDs, and rich-menu management.
✓Restrict the Airtable API key to the bases and write scopes Claude is allowed to use before enabling record or schema changes.
✓Data API Builder MCP tools can expose database entity metadata and perform DML operations depending on DAB configuration and permissions.
Built-in tools include entity discovery and record read, create, update, delete, aggregate, and execute-style workflows in the MCP source tree.
The upstream README still labels endpoint support as coming soon while source, samples, and testing docs expose MCP behavior; verify the exact release before production use.
Use least-privilege roles, disable DML tools where not required, and require approval before write, delete, execute, or stored-procedure operations.
Do not connect MCP clients to production databases without backups, audit logging, query limits, and rollback procedures.
✓Use a least-privilege GitHub token because repository, issue, pull request, and file operations can modify public or private projects.
✓LINE Bot MCP Server can push text and flex messages to users, broadcast messages to all followers, retrieve follower IDs, inspect profiles, check message quotas, create rich menus, set default rich menus, cancel defaults, and delete rich menus.
Broadcast and rich-menu tools can affect every user following the connected LINE Official Account, so require human approval before running them in production.
Push-message tools can contact individual users directly; confirm the target `userId`, message body, and account context before sending.
Rich-menu tools can upload generated menu images and change user-facing navigation for the account.
Use least-privilege channel tokens where possible, keep test and production LINE accounts separate, and monitor quota consumption.
The upstream README marks the project as a preview version for experimental use with potentially incomplete functionality or support.
Privacy notes
✓Airtable records, field values, attachments, and base metadata may be sent through the MCP client and model context.
✓Entity metadata can expose database names, table names, view names, stored procedure names, field names, key fields, relationships, permissions, and role design.
Read and DML tool calls can expose or change customer records, internal data, regulated fields, identifiers, audit fields, and business workflow state.
Connection strings, role headers, MCP URLs, logs, request bodies, result payloads, and MCP transcripts can contain sensitive operational or personal data.
Redact database values, connection details, entity names, role names, and query results before sharing prompts, screenshots, logs, or generated notes.
✓Repository contents, issues, pull requests, comments, org metadata, and user details may be sent through model context.
✓Channel access tokens, destination user IDs, follower IDs, profile display names, profile picture URLs, status messages, language, message contents, flex-message JSON, and rich-menu IDs can be exposed to the MCP client.
Broadcast prompts, generated messages, user IDs, and profile results may be retained in MCP client logs, terminal history, model context, or chat transcripts.
Treat LINE Official Account credentials and recipient identifiers as secrets, and avoid pasting real tokens or user IDs into shared logs.
Review LINE platform policies and internal consent requirements before retrieving follower IDs or using AI-generated outbound messages.
Prerequisites
Node.js 18+ installed for running npx commands and MCP server packages
Airtable Personal Access Token (PAT) from https://airtable.com/account
Base ID for the Airtable base you want to access (starts with 'app' prefix)
Reviewed Azure Data API Builder configuration with the MCP runtime section enabled.
Supported Azure or on-premises database connection configured through DAB.
DAB entity permissions, role headers, DML tool flags, and per-entity MCP settings reviewed before exposing tools.
MCP client support for the transport used by the deployed DAB server.
GitHub account (sign up at https://github.com if needed)
GitHub Personal Access Token with repo scope (generate from GitHub Settings > Developer Settings > Personal Access Tokens)
Docker installed and running (verify with: docker --version)
Internet connection (remote GitHub API access required)
Node.js 22 or newer for the published npm package.
A LINE Official Account with the Messaging API enabled.
A LINE channel access token with the permissions needed for the intended tools.
A destination user ID when using the default recipient flow for push-message tools.
Install
claude mcp add airtable --env AIRTABLE_API_KEY=YOUR_KEY -- npx -y airtable-mcp-server && claude mcp list
Enable the DAB runtime MCP section, start Data API Builder with the reviewed configuration, and connect an MCP client to the configured MCP path.
claude mcp add github -e GITHUB_PERSONAL_ACCESS_TOKEN=YOUR_TOKEN -- docker run -i --rm -e GITHUB_PERSONAL_ACCESS_TOKEN ghcr.io/github/github-mcp-server && claude mcp list