Data Sources
Connect your databases, warehouses, storage, and SaaS apps to MarcoPolo.
MarcoPolo connects to your data wherever it lives. Once connected, your AI can query, browse, correlate, and analyze across any source in a single conversation.
Supported sources
| Category | Platforms |
|---|---|
| Databases | PostgreSQL, MySQL, Microsoft Fabric SQL, ClickHouse, MongoDB |
| Cloud Warehouses | Snowflake, BigQuery, Redshift, Athena |
| Object Storage | AWS S3, Google Cloud Storage, Azure Blob |
| SaaS Apps | Salesforce, HubSpot, Jira, Google Sheets, ClickUp |
50+ connectors and growing. Need something not listed? Contact support@marcopolo.dev.
Adding a data source
Connecting a data source is separate from your MarcoPolo account. Your account establishes who you are; data source connections give your AI access to specific systems.
The fastest way to add one:
You: "I want to add a PostgreSQL database."MarcoPolo generates a link and walks you through the connection flow. The method depends on the source. OAuth for SaaS apps like Salesforce and Google Sheets, username/password for databases like PostgreSQL, service account keys for warehouses like BigQuery, access keys for storage like S3. You don't need to worry about which method applies; MarcoPolo guides you through the right one.
You can also manage connections directly at mcp.marcopolo.dev/app/datasources.
Network requirements
MarcoPolo connects to your data sources over the public internet.
IP allowlisting. If your source requires a firewall allowlist (database firewalls, MongoDB Atlas, etc.), add MarcoPolo's NAT gateway:
34.208.3.240/32Local databases. MarcoPolo can't connect to databases running only on your laptop. Expose them via a tool like ngrok or another secure tunnel.
Private networks. For VPC peering, PrivateLink, or BYOC deployments, contact support@marcopolo.dev.
Sharing with your team
- Open Data Sources in the web UI.
- Select a source and click Share.
- Share with specific people or your entire company (same email domain).
Shared sources appear automatically in teammates' workspaces. Each person gets their own isolated connection. Sharing a source doesn't share your credentials. See Workspace Isolation for details.
Uploading files
You can upload CSV, Excel, and other files directly through the web UI or by asking your AI. They land in your workspace where your AI can read, parse, and analyze them alongside connected data sources.
Detailed guides
Each source type has different connection patterns and best practices:
- Databases: PostgreSQL, MySQL, ClickHouse, MongoDB, Microsoft Fabric
- Cloud Warehouses: Snowflake, BigQuery, Redshift, Athena
- Object Storage: S3, GCS, Azure Blob
- SaaS Applications: Salesforce, HubSpot, Jira, Google Sheets