mcpField
W
Whalesync

Whalesync

Remote
whalesync.comProductivity0Updated 7w ago

About Whalesync

Whalesync is a remote MCP server for AI agents to build and manage data syncs between apps and monitor sync issues. Agents can configure syncs and mappings or investigate unsynced records, while app connections, sync activation, and delete approval remain in the Whalesync app.

Key features

  1. 01Create and update syncs
  2. 02Map and validate tables and fields
  3. 03Activate, pause, or delete syncs
  4. 04Monitor issues and retry them
  5. 05Inspect records and operation status

Use cases

  1. 01Configure a sync between two apps
  2. 02Adjust table and field mappings
  3. 03Investigate and retry unsynced records
  4. 04Check sync status and issues

MCP support

The remote MCP server uses Streamable HTTP and OAuth 2.1 with PKCE. AI agents can call Whalesync API tools; connecting apps, activating syncs, and approving deletions happen in the Whalesync app.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://api.whalesync.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Whalesync MCP server

Whalesync keeps data in two-way sync between the tools your team already uses — Airtable, Webflow, HubSpot, Salesforce, Notion, Postgres, and more.

This repository is the public home of the Whalesync MCP server: a remote Model Context Protocol server that lets AI agents build and manage syncs for you — create a sync between two apps, map tables and fields, turn it on, and monitor it, including answering "why isn't this record syncing?".

  • Server URL: https://api.whalesync.com/mcp (Streamable HTTP)
  • Auth: OAuth 2.1 with PKCE — your client opens a browser to approve access; no API keys to paste. Read-only access is available at consent time.
  • Docs: https://docs.whalesync.com/api/mcp

The server is remote-only. There is nothing to install from this repository — it exists so directories and registries can link to a canonical public source. The server itself is developed elsewhere.

Install

Cursor — Add to Cursor, or add to ~/.cursor/mcp.json:

{ "mcpServers": { "whalesync": { "url": "https://api.whalesync.com/mcp" } } }

Claude Code

claude mcp add --transport http whalesync https://api.whalesync.com/mcp

VS Code

code --add-mcp '{"name":"whalesync","type":"http","url":"https://api.whalesync.com/mcp"}'

Codex

codex mcp add whalesync --url https://api.whalesync.com/mcp

Claude (web, desktop, mobile) — install from the Claude directory — click Connect.

ChatGPT — install from the ChatGPT app directory — click Connect, or add a custom connector with the URL https://api.whalesync.com/mcp.

Grok — grok.com/connectors → New Connector → Custom → paste https://api.whalesync.com/mcp.

On first use, your client opens a browser window to sign in to Whalesync and approve access. You'll need a Whalesync account.

What the agent can do

24 tools over the Whalesync public API:

  • Build: sync_create, sync_update, sync_list_connectors, sync_list_bases, sync_list_tables, sync_list_fields, sync_get_mappings, sync_update_mappings, sync_validate_mappings
  • Run: sync_activate, sync_pause, sync_delete
  • Monitor & fix: sync_get_status, sync_list_issues, sync_get_issue, sync_retry_issue, sync_list_operations, sync_get_operation, sync_search_records, sync_get_record_status, sync_list_pending_deletes
  • Navigate: sync_list, sync_get, sync_whats_next

Tools are prefixed sync_ because they cover Whalesync's sync feature; other features will arrive under their own prefixes.

Anything irreversible stays human-gated: connecting your apps (OAuth), starting a sync, and approving deletes all happen in the Whalesync app — the agent hands you a link at each step.

Support

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.