mcp-server

WrenAI: AI-Powered Insights

Get trusted dashboards from natural-language questions with WrenAI, a tool.
17,346 stars1,959 forksPythonGuide quality 8/10Updated 8/21/2026100% free · open source
What it does

WrenAI turns natural-language questions into trusted dashboards, charts, and SQL across 20+ data sources like BigQuery, Snowflake, and PostgreSQL.

When to use it
  • You need to generate reports from various data sources without manually writing SQL queries.
  • Your team members without technical expertise want to explore data insights using natural language.
  • You want to create a data-driven dashboard with ease, without requiring extensive data engineering knowledge.
Ready-to-paste prompt
What is the total sales revenue for the last quarter from our BigQuery dataset?
Heads up: Make sure you have the necessary credentials and configuration set up for your data sources, as WrenAI will not work without proper authentication and connection details.
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/wrenai && curl -fsSL https://workflowstacks.com/api/skills/wrenai/claude-skill -o ~/.claude/skills/wrenai/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How WrenAI: AI-Powered Insights works
Codeflow
Free to inspect

WrenAI: AI-Powered Insights is a large Python project (~50k lines across 222 code files, plus 144 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Other license, has a test suite.

Size
Large codebase
~50k lines · 222 code files · ~7 h to skim
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Python
No API keys detected
Python 62%Rust 35%HTML 2%JavaScript 1%Shell 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    core/wren-core-base/README.md
    Inside core/ — the main logic begins here
  4. 4
    examples/v5-jaffle/apps/sales-report/index.html
    A worked example — copy this to get going
What's in each folder
core/Core code — the actual logic423 files
skills/Prompts, skills & agent definitions8 files
docs/Documentation87 files
examples/Examples you can copy15 files
sdk/SDKs / client libraries82 files
evals/Evaluations & benchmarks5 files
misc/Folder3 files
scripts/Helper scripts1 files
READMEHas testsDocumentedCI checksExamples includedOther licenseUpdated this month
Quick Actions
Details
Creator
Canner
Language
Python
Category
mcp-server
Published
3/13/2024

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.