text2sql

io.github.cpenniman12Published by GitHub account cpenniman12v0.1.2Updated Oct 24, 2026

Ask any SQL database in natural language. Agent explores schema, writes SQL, self-corrects.

VerifiedSTDIODesktop onlyDatabases AI & ML

Server details

Identifier: io.github.cpenniman12/text2sql-mcp
Transport: STDIO
Runtime: Desktop only
Trust: Verified
Published: Sep 16, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified the GitHub account cpenniman12 for this listing. That does not show the account is the product's maker.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.cpenniman12%2Ftext2sql-mcp.svg)](https://sourceweft.com/mcp/io.github.cpenniman12%2Ftext2sql-mcp?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

Lets an assistant query a SQL database in natural language, exploring the schema, writing and running SQL, and correcting itself on errors.

What you can do: Ask a database a natural-language question and get back the generated SQL, result rows, error and row count.
When to use it: Use it when you want to ask questions of a SQLite, Postgres, MySQL, Snowflake or BigQuery database in plain language without writing SQL or setting up schema descriptions and embeddings first.
Requirements: Runs locally as a Python package (pip or uvx), with a database extra such as postgres, mysql, snowflake or bigquery installed as needed. Requires TEXT2SQL_DATABASE_URL and either ANTHROPIC_API_KEY or OPENAI_API_KEY; optional TEXT2SQL_MODEL, TEXT2SQL_INSTRUCTIONS and TEXT2SQL_EXAMPLES.

Before you install

Needs a database connection URL, which may embed credentials, and an LLM provider API key, both stored in the MCP client config. The assistant executes generated SQL against the real database, so it may write, change or delete data; prefer a read-only account or backups. Questions and schema details are sent to the chosen LLM provider.

Installation

In SourceWeft

Open text2sql in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

text2sql-mcp

MCP server for text2sql-framework. Plugs into Claude Desktop, Cursor, Goose, or any other MCP-compatible assistant and lets it ask a SQL database questions in natural language.

The agent explores the schema, writes SQL, executes it against the real DB, and self-corrects on errors — no RAG layer, no schema descriptions, no pre-computed embeddings.

Install

Out of the box, text2sql-mcp supports SQLite + Anthropic:

For other databases or LLM providers, install with the matching extra so the right driver gets installed:

You want…	Install command
SQLite (default)	`uvx text2sql-mcp`
Postgres	`uvx 'text2sql-mcp[postgres]'`
MySQL	`uvx 'text2sql-mcp[mysql]'`
Snowflake	`uvx 'text2sql-mcp[snowflake]'`
BigQuery	`uvx 'text2sql-mcp[bigquery]'`
OpenAI models	add `openai`, e.g. `uvx 'text2sql-mcp[postgres,openai]'`

Configure

Set environment variables in your MCP client config:

Variable	Required	Description
`TEXT2SQL_DATABASE_URL`	yes	SQLAlchemy URL, e.g. `sqlite:///mydb.db`, `postgresql://user:pass@host/db`
`ANTHROPIC_API_KEY` or `OPENAI_API_KEY`	yes	LLM provider key
`TEXT2SQL_MODEL`	no	LangChain model id (default: `anthropic:claude-sonnet-4-6`)
`TEXT2SQL_INSTRUCTIONS`	no	Business rules / hints, e.g. "Revenue = net of refunds."
`TEXT2SQL_EXAMPLES`	no	Path to a scenarios.md file for the agent's `lookup_example` tool

Claude Desktop / Cursor / generic MCP

json

{  "mcpServers": {    "text2sql": {      "command": "uvx",      "args": ["text2sql-mcp"],      "env": {        "TEXT2SQL_DATABASE_URL": "sqlite:///mydb.db",        "ANTHROPIC_API_KEY": "sk-ant-..."      }    }  }}

{  "mcpServers": {    "text2sql": {      "command": "uvx",      "args": ["text2sql-mcp"],      "env": {        "TEXT2SQL_DATABASE_URL": "sqlite:///mydb.db",        "ANTHROPIC_API_KEY": "sk-ant-..."      }    }  }}

Goose CLI

bash

goose configure# Add Extension → Command-line Extension# Name: text2sql# Command: uvx text2sql-mcp# Env: TEXT2SQL_DATABASE_URL, ANTHROPIC_API_KEY

goose configure# Add Extension → Command-line Extension# Name: text2sql# Command: uvx text2sql-mcp# Env: TEXT2SQL_DATABASE_URL, ANTHROPIC_API_KEY

Tools

query(question, max_rows=100) — ask the database a natural-language question. Returns {sql, data, error, row_count, tool_calls_made}.

How it works

Under the hood this is a thin wrapper around text2sql-framework, which uses LangChain Deep Agents to do iterative tool-calling against a single execute_sql tool. See the framework README for benchmarks (19/20 on Spider zero-shot across 80 tables) and architecture details.

License

MIT

Source: README.md at commit 97142b4

Tools

SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

v0.1.2LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
License10 pts