← Index

text2sql

io.github.cpenniman12/text2sql-mcp·v0.1.2·Other

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

Trust verdict · v1 advisory · method
NOT YET SCREENEDno verdict on file

Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.

Own this server? Screen its description →

Environment variables
TEXT2SQL_DATABASE_URL
required

SQLAlchemy connection URL, e.g. sqlite:///mydb.db or postgresql://user:pass@host/db

ANTHROPIC_API_KEY
secret

Anthropic API key (required if using the default Anthropic model)

OPENAI_API_KEY
secret

OpenAI API key (required when TEXT2SQL_MODEL is set to an openai:* model)

TEXT2SQL_MODEL

Optional LangChain model id (default: anthropic:claude-sonnet-4-6)

MCP quality score · maturity, not trust · methodology
freshness
25
completeness
15
installability
25
documentation
15
stability
5
Alternatives in Other