Wren Engine CLI and Python SDK — semantic SQL layer for 20+ data sources
Wren MCP server exists for a simple reason — assistants are far more useful when they can act on Wren directly instead of describing what you should do. Wren Engine CLI and Python SDK — semantic SQL layer for 20+ data sources.
Generative BI (GenBI) is business intelligence produced by AI agents: instead of manually building charts, an agent generates governed SQL, deploys a dashboard, and shares it — grounded in an AI context layer so the output is trustworthy, not just plausible. Wren AI is the open-source GenBI engine.
Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
Once Wren is connected, these are the calls the assistant has available:
Engine — Apache DataFusion based, 22+ data sources (BigQuery, Snowflake, PostgreSQL, ClickHouse, Amazon Redshift, Databricks, DuckDB, and more)End-to — end correctness primitives**: value profiling, rich retrieval, structured errors, golden eval runnerAgent — native distribution**: first-class SDKs across major agent frameworks; see GitHub Discussions forRow — and column-level security (RLS / CLS)** and access control with users & groupsYou will need one environment variable: HF_ENDPOINT. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
This sits in the database access group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Wren's toolset — Engine, End-to, Agent and 1 more — is a fair guide to whether it matches your workflow.
This entry was verified against Wren's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Engine | Apache DataFusion based, 22+ data sources (BigQuery, Snowflake, PostgreSQL, ClickHouse, Amazon Redshift, Databricks, DuckDB, and more) |
| End-to | end correctness primitives**: value profiling, rich retrieval, structured errors, golden eval runner |
| Agent | native distribution**: first-class SDKs across major agent frameworks; see [GitHub Discussions](https://github.com/Canner/WrenAI/discussions) for what's prioritized next |
| Row | and column-level security (RLS / CLS)** and access control with users & groups |
{
"mcpServers": {
"wren-engine": {
"command": "npx",
"args": ["-y", "skills"],
"env": {
"HF_ENDPOINT": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| HF_ENDPOINT | Configuration value read at startup. | Optional |
Read-only SQL access to Postgres — let your assistant inspect schemas and answer questions from real data.
Manage your whole Supabase project in conversation — database, auth, storage, Edge Functions and branches.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Official MongoDB server covering data, schemas and Atlas management — from find queries to spinning up clusters.
Serverless Postgres with database branching — point your assistant at Neon and let it work on disposable copies.