About shebanq-mcp

Query the BHSA Hebrew Bible in plain language, and keep the query.

What is this for

shebanq-mcp is a front door to the BHSA, the ETCBC's linguistic database of the Hebrew Bible. You ask in plain language; the answer is a real, runnable, citable query in two languages, with its results. The query stays in your hands the whole way.

It serves three kinds of work:

• Learning the database. The hardest part of querying the BHSA was never the syntax; it is knowing which feature encodes the phenomenon you care about. That Niphal lives in vs. That a verb lexeme carries a trailing [. That gender is encoded on the word as a form, so "feminine plural nouns" counts forms, which may differ from what a grammar means by gender. Watching real queries form from your own questions, with every feature visible and validated, teaches that mapping faster than any manual.
• Working in SHEBANQ. A first draft of your query in seconds, yours to read, correct, run, and save on SHEBANQ as a citable permalink. The draft is a starting point; the judgment stays with you.
• Working in Text-Fabric. Every answer carries the Text-Fabric equivalent of its query, derived by plain code, and the converter turns your notebook template into SHEBANQ-citable MQL. Two ecosystems, one corpus, one door between them.

One honest caution, because it is the most important thing on this page: a query can be perfectly valid and still encode a different question than you meant. Validation catches malformed queries; it cannot catch a faithful answer to the wrong question. That is why the query is always shown, why the examples carry engine-verified counts, and why a conversion that would change a query's meaning is refused with the reason. Read the query before you cite it. This tool is built to make that reading easy. Each answer also lists what its query assumes about BHSA's encoding, so a valid query that answers a slightly different question than you meant is caught before it is cited.

How to use

Ask, read the query, run it

Type a question the way you would ask a colleague: "all feminine plural nouns", "where does bara occur?". Click Translate to MQL and the generated query appears, editable, before anything runs. Read it. Change it if you like. Then Run query executes it against the BHSA and the results come back with vocalized Hebrew, glosses, and counts. Beside every MQL query the answer also shows its Text-Fabric equivalent, derived by plain code, for scholars who work in notebooks.

The reference checkbox wraps the query in a verse block so each hit carries its book, chapter, and verse. Untick it for the plain form. Toggling never re-translates; it switches between the two forms of the same query.

The converter

The TF → MQL converter (link at the top) exists for citation. Work in your Text-Fabric notebook, paste your search template into the converter, and take the resulting MQL to SHEBANQ: save it there and you have a permanent link you can cite in print, one your readers can click and re-run. The conversion is deterministic, plain code with no AI involved, so the same input always gives the same output. A template using constructs MQL cannot express is refused with a plain explanation, never converted approximately. Note the data version when you cite: this server is pinned to ETCBC 2021.

From an MCP client

The same engine is a remote MCP endpoint: https://shebanq-mcp.onrender.com/mcp. Add it in Claude.ai under Settings → Connectors → Add custom connector, or bridge it with mcp-remote in any client that loads local servers (details in the README).

The tools, one line each:

• search_bhsa(question): plain language in, a citable query in both languages plus results out.
• run_mql(mql): validate and run an MQL query you already have.
• run_tf(template): validate and run a Text-Fabric search template.
• to_citable_mql(template): Text-Fabric template in, SHEBANQ-citable MQL out. No model involved.
• to_tf_template(mql): the mirror; MQL in, Text-Fabric template out.
• lookup_feature(name): a BHSA feature's meaning and valid values.

Methodology

Generative AI can draft a database query from a plain-language question. That raises a fair worry for scholarship: if a machine writes the query, does the scholar still learn anything? This project takes a position. The translation was never the whole of the work. The scholarly act is judging whether a query faithfully captures a form-to-function question, and reading what a result does and does not show. So the design keeps the query visible and central:

• The query is the product. Every result carries the exact query that produced it, in two languages: Emdros MQL, which pastes straight into SHEBANQ to save and cite, and a Text-Fabric search template for notebook research. Nothing comes back as a black box.
• Validation before execution. Every query is checked against the BHSA feature catalogue before it runs. A wrong code like vs=niphal (the correct code is vs=nif) fails loudly with the reason, instead of silently returning zero. That catalogue is itself generated from the engine (its object types, kinds, and the values that actually occur in the data) and kept in step by a round-trip test, so what a query is checked against is the engine's own structure, not a hand-kept list.
• Honest empty results. Zero matches returns the query and a plain "0 results", so you can tell "the query is wrong" from "the phenomenon is not there".
• One dataset, two engines, equal answers. Both engines are pinned to the BHSA 2021 release. A test suite proves on every change that the same question returns the same counts from both, so the two query languages are genuinely interchangeable. One labeling difference to know: Text-Fabric notebooks display English book names (Deuteronomy) where SHEBANQ shows the ETCBC names (Deuteronomium); same verses, different labels.
• Conversion without a model. The MQL ⇄ Text-Fabric converter is deterministic code. What you cite is exactly what ran, and a query that cannot be expressed in the other language is refused with the reason. A test suite re-proves on every change that a derived template returns the identical result rows on Text-Fabric as its source MQL does on Emdros, so a citation returns what the notebook returned.
• The model has a small, bounded role. Only the plain-language translation uses an AI model, behind a swappable interface and a spend cap. Everything downstream of the generated query, validation, execution, conversion, and formatting, is ordinary verifiable code.

AI as a way in, not a way around.

Data and credits

The linguistic data is the BHSA (ETCBC 2021), created and maintained by the Eep Talstra Centre for Bible and Computer. Queries run on the Emdros text database engine and on Text-Fabric. SHEBANQ hosts the citable saved queries this project links into.

Built by Jose Fresco Benaim. Source on GitHub, archived with DOI 10.5281/zenodo.20625355.

---

← Back to the web app