Anomalo MCP Server

Documentation

Documentation link · transport stdio

Tools

• get_organizations — Retrieves a list of accessible organizations from the Anomalo deployment, including which organization is currently active for the given API key. Schema is `{id: int, name: str, is_active: bool}`. Each organization is a tenant within the Anomalo deployment.
• set_active_organization — Sets the active organization for API access. API calls are scoped to the active organization, which is sticky across calls.
• get_labels — Retrieves the labels in the active organization. Labels organize tables and checks. Each has an id, name, URL-friendly slug, and a scope indicating whether it applies to tables, checks or both.
• get_configured_tables — Retrieves the configured tables in the active organization, optionally filtered by label name, table name or table id.
• get_table_data_profile — Retrieves a profile of the data in a table from Anomalo's analysis of sampled data — column value samples, per-column statistics (type, null %, uniqueness, min/max, mean, median, stddev, skew, kurtosis) and rendered image URLs. Only available for monitored tables.
• get_table_check_status — Retrieves the data quality health of a table by locating the last completed check run and returning every check result, including failure descriptions, root cause analysis, and links to CSV samples of bad/good rows plus the SQL to retrieve them.
• get_checks_for_table — Retrieves the data quality checks configured for a table — check_id, check_static_id, name, description, active flag and severity.
• run_data_quality_checks_on_table — Triggers a data quality check run on a table, or a single check when check_id is given. Returns a check_run_id. Does not wait for completion, and will not start a run if one is already pending.
• data_quality_check_run_status — Retrieves the results of a check run by check_run_id. Status is one of pending, running, completed or failed.

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.