Google Calendar MCP in Claude Code

Quick answer: Install the Google Calendar MCP server with npx -y @cocal/google-calendar-mcp, 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 @cocal/google-calendar-mcp as of April 15, 2026.

The Google Calendar MCP server hands Claude Code a tool surface on Google Calendar. After OAuth setup, the model can read your schedule, create events, check busy times across calendars, and invite attendees. For scheduling conversations inside the editor, this is the fastest way to let Claude check your calendar and draft a new event without a browser round trip.

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 Google Calendar 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 Google Calendar day to day, this replaces dozens of context switches per week with a single line in chat.

Tools exposed: list_calendars, list_events, create_event, update_event, delete_event, get_freebusy, search_events. The create_event tool supports attendees with RSVP handling, Meet link auto-generation, and conference data. Recurring events can be edited on the single-instance or series level; the tool takes a recurrence_id parameter to target which.

Prerequisites

A Google Cloud project with the Calendar API enabled. OAuth 2.0 client credentials (JSON) downloaded to a local path. Node 20 or later. The account you authorize with must have access to the calendars you want to query.

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 @cocal/google-calendar-mcp

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": {
    "google-calendar": {
      "command": "npx",
      "args": ["-y", "@cocal/google-calendar-mcp"],
      "env": {
        "GOOGLE_OAUTH_CREDENTIALS": "/Users/you/.claude/gcal-creds.json",
        "GOOGLE_CALENDAR_MCP_TOKEN_PATH": "/Users/you/.claude/gcal-token.json"
      }
    }
  }
}

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:

• What events do I have on my primary calendar for next Tuesday between 9am and 6pm?
• Create a 30-minute meeting titled Design review with alice@example.com and bob@example.com for tomorrow 2pm local time.
• Find a 60-minute slot where alice@example.com bob@example.com and I are all free next week afternoons.
• List every event in the next 7 days that mentions the word interview in the title.
• Move the event with ID abc123 from 3pm to 4pm on the same day and notify attendees.
• Cancel every meeting I have on Friday April 24 and send decline notes to attendees.

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

Two env vars: GOOGLE_OAUTH_CREDENTIALS pointing at the client secret JSON, GOOGLE_CALENDAR_MCP_TOKEN_PATH pointing at where the refresh token will be stored after first login. Both files must be read-write for the Claude user and read-restricted (chmod 600). Never commit either file.

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

First login loops without returning a token. The OAuth consent screen needs the right scopes enabled. In the Google Cloud console, verify the Calendar API is enabled and the OAuth consent screen includes https://www.googleapis.com/auth/calendar in its scopes.

Tool calls return insufficient authentication scopes. The token was issued with read-only scopes but you are trying to write. Delete the token file, edit the OAuth config to request the full calendar scope, and re-authorize.

Events do not appear in the right timezone. The server uses the calendar default timezone for times without a TZ specifier. Ask Claude to include the timezone in the prompt, or update the primary calendar timezone in Google Calendar settings.

FreeBusy query returns empty results. The account you authorized must have visibility into the other attendees' calendars. For Workspace, this usually works out of the box; for external accounts, the other calendars must share free-busy info publicly.

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 Google Calendar 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.