Airtable MCP in Claude Code

Quick answer: Install the Airtable MCP server with npx -y airtable-mcp-server, add the JSON block below to ~/.claude/settings.json, restart Claude Code, and run /mcp to confirm the connection. Setup runs about 5 minutes on a fresh machine, verified on airtable-mcp-server as of April 15, 2026.

The Airtable MCP server gives Claude Code a tool surface on the Airtable API. After setup, the model can list bases, describe schemas, read records with filters and sorting, create rows, and update or delete entries. The server is published as airtable-mcp-server and uses a personal access token for auth.

This guide covers what you get after the wiring is done, the exact config, verification steps, prompt patterns that tend to work well, and the 4 issues that trip people up most often in the first week.

What you get when it is connected

Once the Airtable server is attached, Claude Code can call the server tools from inside any conversation. You do not invoke the tools by hand. When you ask Claude a question the model decides which tool to call and parses the response for you. For teams that live inside Airtable day to day, this replaces dozens of context switches per week with a single line in chat.

Tools exposed include list_bases, list_tables, describe_table, list_records, get_record, create_records, update_records, delete_records, search_records. Every call is a live API round trip with no local cache, so expect 200 to 400 ms per call. Attachments are returned as metadata URLs only - the server does not download binary payloads.

Prerequisites

An Airtable account, a personal access token from airtable.com/create/tokens with scopes data.records:read, data.records:write, and schema.bases:read. The token must be granted the specific bases you want Claude to touch.

If you use a version manager like nvm or asdf for Node, confirm the version Claude Code inherits. Open a terminal, run node -v, and note the output. Claude Code uses the Node it sees on PATH at launch, so a shell profile that sets the right version is the reliable path.

Install via npx

Run the package once with npx to verify it starts cleanly:

npx -y airtable-mcp-server

The first run downloads the package (a few MB) and starts the server on stdio. The server does not print much on success - it waits for MCP protocol messages on stdin. Press Ctrl-C to stop it. The actual runtime setup happens through Claude Code itself in the next step.

If the install fails with a network error, your npm registry may be blocked. Set npm config set registry https://registry.npmjs.org and retry. Behind a corporate proxy, also set HTTP_PROXY and HTTPS_PROXY in your shell.

Add the config block to ~/.claude/settings.json

Open ~/.claude/settings.json in your editor. If the file does not exist yet, create it with {} as the starting content. Add an mcpServers object with an entry for this server:

{
  "mcpServers": {
    "airtable": {
      "command": "npx",
      "args": ["-y", "airtable-mcp-server"],
      "env": {
        "AIRTABLE_API_KEY": "patXXX"
      }
    }
  }
}

Save the file. If you already have other MCP servers defined, merge the new entry into the existing mcpServers object rather than replacing it.

Restart Claude Code fully (quit and reopen, not just close the window). The server is spawned lazily on the first tool call in a session, not at launch, but the config is read once per Claude Code start.

Verify the connection

Open a new Claude Code session and type /mcp at the prompt. You should see the server listed with a green or connected indicator. If it shows as failed, click into it for the stderr output - the error message usually points at the problem directly (bad token, wrong path, missing Node).

Run a trivial first prompt to confirm round trips work. Good smoke tests:

• For read servers: ask for a list of whatever resource type it exposes.
• For write servers: ask for a describe on a known resource first, then try a safe write on a test resource.

If the first prompt works, the wiring is done. From here on you interact with the server purely through normal prompts in Claude Code.

Example prompts that work well

Here are prompts that tend to get good responses once the server is attached:

• List every base my token has access to and tell me what each one tracks.
• Read the Customers table in the CRM base and show every row where plan equals Enterprise.
• Create a new record in Feedback with source email, priority high, and the summary I paste below.
• Update the Status field on record recXYZ to Closed and add a note in the Activity field.
• Search the Leads table for any record that mentions acme.com and return the matching fields.
• Describe the schema of the Projects base and tell me the types for every field.

Claude will chain tool calls on its own when the prompt implies several steps. For a summarize-then-write flow the model will often call read tools first, then a single write tool at the end. If a prompt keeps burning tool calls, narrow it: specify the resource ID, the time range, or the exact field you want rather than asking Claude to scan everything.

Environment variable security

The token lives in AIRTABLE_API_KEY. Store it as a shell env var, not in committed config. Scope the token to specific bases rather than All current and future bases, so a mistaken prompt cannot touch the rest of the workspace. Rotate from airtable.com/create/tokens if it leaks.

A general rule across every MCP server: never paste secrets directly into settings.json that lives in a shared or git-tracked directory. Keep the actual secret values in your shell profile (~/.zshrc, ~/.bashrc, or a 1Password-cli helper), export them at shell start, and reference the variable names from the Claude config. That way the secret stays on your machine and the config file is safe to share with teammates.

On macOS, terminals launched from Spotlight or from the Dock both inherit the shell profile. If you launch Claude Code from a GUI shortcut that does not go through a shell, env vars may not propagate - launch from a terminal instead.

Troubleshooting

Tool calls return 401. The token is wrong or has been revoked. Regenerate at airtable.com/create/tokens, add the right scopes, add the bases you need, and update the env var. Restart Claude Code.

Tool calls return 403. The token is valid but the base is not in its scope. Edit the token, add the base, and retry. Legacy API keys (pre-2024) no longer work at all - only personal access tokens starting with pat are accepted.

Rate limit errors at 5 req/sec. Airtable caps at 5 requests per second per base. Bulk updates fail when Claude fires off too many at once. Ask Claude to batch updates into groups of 10 rows per call, which cuts request count significantly.

Filter formula returns wrong rows. Airtable formulas are strict about field references. Use curly braces for multi-word field names: {Due Date} not Due Date. Test the formula in the Airtable UI first if in doubt.

For any issue not listed here, the first step is /mcp inside Claude Code to see the current status and any recent stderr from the server. The second step is running the exact npx command from your terminal to see if the server starts cleanly outside Claude Code. Between those two checks, most problems become obvious within a minute.

Next steps

Once the Airtable server is attached and verified, the useful next move is writing a short prompt template you keep in your notes. List the 3 or 4 prompts you run most often against this server, and paste them into Claude Code when needed. Over a few weeks you build a personal command library that gets real work done without typing much.

For team projects, commit a .mcp.json at the repo root with the same structure. Everyone on the team gets the server wired up automatically on first open, and individual secrets stay in shell profiles. That is the setup pattern that scales past a single developer.