Skip to main content

MCP server for Fivetran API - manage syncs, check status, and control connections

Project description

Fivetran MCP Server

License: MIT Python 3.10+ Built by Claude Code

Note: This repository is built and maintained entirely by Claude Code, Anthropic's AI coding assistant.

An MCP (Model Context Protocol) server for controlling Fivetran data pipelines. Enables AI assistants like Claude to manage syncs, monitor connection status, and control data pipelines through natural language.

Features

  • List connections - View all Fivetran connections with status
  • Check sync status - Get detailed status for any connection
  • Trigger syncs - Start syncs on demand
  • Historical resync - Trigger full data resync or resync specific tables
  • Pause/Resume - Control connection scheduling
  • List groups - View all destination groups
  • Test connection - Diagnose connectivity and configuration issues

Quick Start

Step 1: Clone the Repository

git clone https://github.com/YimingYAN/fivetran-mcp.git
cd fivetran-mcp
uv sync

Step 2: Get Fivetran API Credentials

  1. Log in to Fivetran Dashboard
  2. Click your username (top right corner)
  3. Click API Key
  4. Click Generate API key
  5. Copy both the API Key and API Secret (secret shown only once!)

See Fivetran API Getting Started for more details.

Step 3: Store Credentials

Add to your ~/.env.local (or equivalent):

# Fivetran API
export FIVETRAN_SYNC_API_KEY="your-api-key"
export FIVETRAN_SYNC_API_SECRET="your-api-secret"

Then reload:

source ~/.env.local

Step 4: Verify Credentials

Test that your credentials work:

curl -s -X GET "https://api.fivetran.com/v1/account/info" \
  -H "Accept: application/json" \
  -H "Authorization: Basic $(echo -n "$FIVETRAN_SYNC_API_KEY:$FIVETRAN_SYNC_API_SECRET" | base64)"

Expected response:

{"code":"Success","data":{"account_id":"...","account_name":"..."}}

Step 5: Configure Claude Code

Add to your ~/.claude.json:

{
  "mcpServers": {
    "fivetran": {
      "type": "stdio",
      "command": "uv",
      "args": ["run", "--directory", "/path/to/fivetran-mcp", "fivetran-mcp"],
      "env": {
        "FIVETRAN_SYNC_API_KEY": "${FIVETRAN_SYNC_API_KEY}",
        "FIVETRAN_SYNC_API_SECRET": "${FIVETRAN_SYNC_API_SECRET}"
      }
    }
  }
}

Replace /path/to/fivetran-mcp with the actual path (e.g., ~/Playground/fivetran-mcp).

Step 6: Restart Claude Code

Restart Claude Code to load the new MCP server. You should now have access to Fivetran tools.

Available Tools

Tool Description
list_connections List all connections, optionally filtered by group
get_connection_status Get detailed status for a connection
trigger_sync Start a sync for a connection (optional force flag)
trigger_resync Trigger full historical resync
resync_tables Resync specific tables only (e.g., ["schema.table_name"])
pause_connection Pause a connection
resume_connection Resume a paused connection
list_groups List all groups/destinations
test_connection Run diagnostic tests to identify connectivity/configuration issues

Environment Variables

The server supports two naming conventions:

Preferred Alternative
FIVETRAN_SYNC_API_KEY FIVETRAN_API_KEY
FIVETRAN_SYNC_API_SECRET FIVETRAN_API_SECRET

Development

# Install dependencies
uv sync

# Run the server locally
uv run fivetran-mcp

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

fivetran_mcp-0.1.0.tar.gz (8.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

fivetran_mcp-0.1.0-py3-none-any.whl (8.1 kB view details)

Uploaded Python 3

File details

Details for the file fivetran_mcp-0.1.0.tar.gz.

File metadata

  • Download URL: fivetran_mcp-0.1.0.tar.gz
  • Upload date:
  • Size: 8.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.7

File hashes

Hashes for fivetran_mcp-0.1.0.tar.gz
Algorithm Hash digest
SHA256 06c6b66fcbb130ceeefad0eecb3a562d09d35ee658d270aa5403dc4e51881e02
MD5 95b59898207306b713755981ad199b6b
BLAKE2b-256 08e51ee90648a439394e95dacd9cef242a13a576dc241f5fb30d474342aa0fa3

See more details on using hashes here.

File details

Details for the file fivetran_mcp-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for fivetran_mcp-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 48764fc1e104af462c976d9abb2e1c3ec25755805d5f16bba18e015a1c627527
MD5 074c88bbffc3da480b599d8c24f49408
BLAKE2b-256 6802abe3ee2ec8be7f8e38fb36c8657324fa0c813b8a8196180244dec388daa5

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page