Tellius MCP Server
Tellius exposes its analytics engine through an MCP server that runs inside each Tellius deployment. The server holds no data of its own — it forwards each request to Kaiya, which interprets the question, generates the SQL, runs the analysis and returns the result, so Business View metric definitions, joins, hierarchies and row-level security continue to apply. Any MCP-compatible client (Claude Code, Claude Desktop, Cursor, or one you build) can connect.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Documentation
Documentation link · transport
Tools
tellius_list_business_views— Search and page through Business Views. The starting point for most work.tellius_get_business_view_details— Full column schema, data types and sample values for one Business View.tellius_list_datasets— Raw imported datasets, before they are modeled into a Business View.tellius_list_connections— Configured data source connections.tellius_ask— Natural-language question answered as SQL and results.tellius_deep_insight— Multi-step agentic investigation for "why" questions.tellius_get_starter_questions— Suggested questions for a Business View.tellius_send_feedback— Record a thumbs up or down on a previous Kaiya response.tellius_list_workflows— Paginated list of workflows and Kaiya Missions.tellius_search_workflows— Search workflows by name or description.tellius_get_workflow— Full step detail for one workflow or Mission.tellius_create_workflow— Author a new reusable multi-step workflow.tellius_update_workflow— Change the name, steps, state or Business Views.tellius_delete_workflow— Permanent delete.tellius_run_workflow— Execute a workflow headlessly. May pause for input before starting.tellius_resume_workflow— Continue a run that paused mid-execution, using its conversation_id.tellius_create_schedule— Recurring delivery of a saved workflow or an ad-hoc question.tellius_list_schedules— Schedules belonging to the calling user.tellius_get_schedule— Full delivery configuration for one schedule.tellius_update_schedule— Pause, resume, or change cadence and delivery channels.tellius_delete_schedule— Permanent delete.tellius_list_slack_channels— Channel ids for Slack delivery on a schedule.tellius_list_teams_channels— Channel and team ids for Teams delivery on a schedule.tellius_remember_user_preference— Save a memory (a rule, a definition or an instruction) that later turns will recall.tellius_list_user_memories— Review saved memories.
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.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.