This is a paid feature. To set up a new integration, contact your Customer Success Manager or email support@datarails.com.
FinanceOS AI Integration (MCP)
FinanceOS allows you to securely connect your AI assistant to your Datarails financial data.
Using the Model Context Protocol (MCP), you can analyze data, profile tables, run queries, generate reports, and extract validated financials directly from the AI platform you already use.
FinanceOS works with:
Claude Code
Claude CoWork
Claude.ai
ChatGPT
Lovable
CoPilot - Coming soon
What You Can Do
Once connected, your AI assistant can:
Discover available financial tables
Understand schema and relationships
Profile data quality
Detect anomalies
Run filtered queries
Perform aggregations
Generate Excel intelligence workbooks
Extract validated financials
Produce charts and reports
All access is securely authenticated via OAuth.
Connecting Your AI Assistant
FinanceOS provides a secure MCP endpoint:
https://mcp.datarails.com/mcp
Authentication is handled automatically using OAuth 2.1.
On first connection, your AI client will redirect you to log in.
Setup Instructions by Platform
Claude Code
Run:
claude mcp add datarails-finance-os --transport http https://mcp.datarails.com/mcp
Restart Claude Code.
The server will appear in your MCP tools list.
You will be prompted to authenticate on first use.
Claude Desktop
Add the following to your claude_desktop_config.json:
{
"mcpServers": {
"datarails-finance-os": {
"type": "streamable-http",
"url": "https://mcp.datarails.com/mcp"
}
}
}Restart Claude Desktop and authenticate when prompted.
ChatGPT, Gemini, or Other MCP Clients
Configure your MCP client with:
https://mcp.datarails.com/mcp
The client will redirect you to log in on first connection.
Available FinanceOS AI Tools
1. Discovery and Profiling
| Tool | What It Does |
|---|---|
list_finance_tables |
Discover available financial tables |
get_table_schema |
View column names, types, and relationships |
get_field_distinct_values |
See unique values in a field |
profile_table_summary |
Row counts and data quality score |
profile_numeric_fields |
Min, max, averages, outliers |
profile_categorical_fields |
Category frequencies and cardinality |
detect_anomalies |
Automatically identify data issues |
2. Querying and Aggregation
| Tool | What It Does |
|---|---|
get_records_by_filter |
Retrieve filtered records (up to 500 rows) |
get_sample_records |
Get a random sample of data |
execute_query |
Run SQL-like queries (up to 1,000 rows) |
aggregate_table_data |
Perform grouped aggregations with no row limit |
3. Reports and Workflows
| Tool | What It Does |
|---|---|
get_workflow_guide |
Step-by-step workflows for common analysis tasks |
generate_intelligence_workbook |
Generate an FP&A intelligence workbook (Excel) |
extract_financials |
Export validated financial data to Excel |
Security and Authentication
FinanceOS uses:
OAuth 2.1 authentication
Secure token encryption
Rate limiting
Enterprise-grade hosting
You will always authenticate through Datarails before your AI assistant can access your data.
No credentials are stored in your AI client.
Data Hosting and Transmission
The FinanceOS MCP service is hosted in the United States.
All data exchanged between your AI client and Datarails is encrypted in transit using secure HTTPS. Only the data required to fulfill a specific request is transmitted, and access remains limited to your existing Datarails user permissions.
No full dataset replication occurs as part of the MCP integration.
Frequently Asked Questions
Is my financial data secure?
Yes. All access is authenticated via OAuth and encrypted in transit. FinanceOS follows enterprise security best practices.
Does this give AI access to all my data?
Only data you have permission to access in Datarails is available through FinanceOS.
Are there query limits?
Yes:
Filtered queries: up to 500 rows
Custom queries: up to 1,000 rows
Aggregations: no row limit
Do I need to install anything in Datarails?
No. FinanceOS works via secure API integration.
Need Help?
If you need assistance connecting your AI platform to FinanceOS, contact Datarails Support or your Customer Success Manager.
© Datarails Ltd. All rights reserved.
Updated
Comments
0 comments
Please sign in to leave a comment.