# Agentic BI in Slack: MCP-powered analytics and visualisations

DevFeed: [Agentic BI in Slack: MCP-powered analytics and visualisations](<https://devfeed.tech/articles/agentic-bi-in-slack-mcp-powered-analytics-and-visualisations-4918.md>)

Original publisher: [Read original article](<https://clickhouse.com/blog/agentic-bi-in-slack-mcp-visualisations>)

Author: Al Brown

Published: 2025-08-27T00:00:00Z

Content type: article

Language: en

Sources: [ClickHouse Blog](<https://devfeed.tech/sources/clickhouse-blog.md>)

Topics: [clickhouse](<https://devfeed.tech/topics/clickhouse.md>), [Model Context Protocol (MCP)](<https://devfeed.tech/topics/model-context-protocol-mcp.md>), [Slack](<https://devfeed.tech/topics/slack.md>), [Python](<https://devfeed.tech/topics/python.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Grafana](<https://devfeed.tech/topics/grafana.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [dashboards](<https://devfeed.tech/topics/dashboards.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [clickhouse](<https://devfeed.tech/tags/clickhouse.md>), [code](<https://devfeed.tech/tags/code.md>), [context](<https://devfeed.tech/tags/context.md>), [dashboards](<https://devfeed.tech/tags/dashboards.md>), [image](<https://devfeed.tech/tags/image.md>), [json](<https://devfeed.tech/tags/json.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [python](<https://devfeed.tech/tags/python.md>), [slack](<https://devfeed.tech/tags/slack.md>), [sql](<https://devfeed.tech/tags/sql.md>), [visualization](<https://devfeed.tech/tags/visualization.md>)

## AI overview

This article describes a chat-native business intelligence layer in Slack built with ClickHouse and MCP. It explains how users can ask analytical questions in natural language, have an LLM generate SQL through MCP tools, execute queries directly in ClickHouse, and receive both visualizations and the exact SQL. The updated implementation generates Vega-Lite JSON specifications, renders charts with a Python bot using vega-altair, and attaches PNG images to Slack threads.

## Source excerpt

Traditional BI assumes a dashboard is the destination. Most often, the destination is a conversation. We're not replacing BI; we're right-sizing it. Dashboards remain for curated KPIs. Chat picks up the fluid, investigative 80%.