datarails-finance-os

Endpoint

Hosted endpoint · transport http

Connect

This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):

For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:

If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:

Tools

• list_data_models — Entry point for both raw data layers. Lists available finance tables / data models; each entry carries the numeric id (for the by-id tools) and the alias (for the by-alias tools; empty when a table has no alias).
• list_aliased_fields — Lists the aliased (friendly-named) fields of a table. Preferred raw-data entry point — roughly 95% fewer tokens than the by-id layer. A table alias does not imply its fields are aliased.
• get_fields_by_id — Returns column names, types and relationships for a table by numeric id.
• list_business_metrics — Lists the org's named business metrics (KPI catalog). Ungated, so it is the discovery entry point for the business-metrics layer even where the metric-data tools are feature-flag denied.
• profile_numeric_fields — Baseline numeric statistics (SUM/AVG/MIN/MAX/COUNT) per field, relayed in the backend-native DR_Values / col_keys / row_keys layout.
• profile_categorical_fields — Category frequencies and cardinality. Must be given an explicit business-dimension field list, or it profiles upload/mapping metadata columns rather than business data.
• get_data_by_alias — Retrieve filtered rows from an aliased table (max 500 rows per page).
• get_data_by_id — Retrieve filtered rows from a table by numeric field ids (max 500 rows per page).
• start_aggregation_by_alias — Start a grouped aggregation over an aliased table. Non-blocking; returns {status: pending, handle}. No row limit on the result.
• get_aggregation_result_by_alias — Poll for the result of start_aggregation_by_alias. status "running" plus retry_after_seconds means poll again; it is not an error.
• start_aggregation_by_id — Start a grouped aggregation over a table addressed by numeric field ids.
• get_aggregation_result_by_id — Poll for the result of start_aggregation_by_id.
• get_aggregated_data_by_alias — Blocking aggregation over an aliased table.
• get_aggregated_data_by_id — Blocking aggregation over a table by numeric field ids.
• start_distinct_values_by_alias — Start a distinct-values fetch for an aliased field. Non-blocking.
• get_distinct_values_result_by_alias — Poll for distinct values started by start_distinct_values_by_alias; takes the limit argument.
• start_distinct_values_by_id — Start a distinct-values fetch for a field addressed by numeric id.
• get_distinct_values_result_by_id — Poll for distinct values started by start_distinct_values_by_id.
• get_distinct_values_by_alias — Blocking distinct-values fetch for an aliased field.
• get_distinct_values_by_id — Blocking distinct-values fetch for a field by numeric id.
• get_business_metric_details — Definition and metadata for one named business metric.
• get_business_metric_data — Values for one named business metric.
• get_business_metric_drilled_down_data — Drill a business metric down by a dimension.
• get_business_metric_table_rows — Underlying rows behind a business metric.
• sql_query — Free-form SQL over the org's finance tables.

About MCP

The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.

Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.