For Agents
Manage language and lexeme records for linguistic field-work projects through the DLx REST API.
Get started with DLx in minutes using your preferred integration method.
# Add to your MCP client config (Claude Desktop, Cursor, Windsurf)
{
"jentic": {
"url": "https://api.jentic.com/mcp",
"auth": "oauth"
}
}
# Then ask your agent:
"list lexemes for a language in dlx"
# → Jentic returns the GET /events tool with parameter schema, agent executes.What an agent can do with DLx API.
Catalogue languages with metadata such as ISO codes, family, and location
Store and retrieve lexeme entries linked to a language record
Look up entries by language and lexeme identifier
Update lexeme glosses, transcriptions, and morphological data
Browse the corpus of languages registered in the DLx system
GET STARTED
Use for: I need to add a new language record to DLx, Retrieve all lexemes for a specific language, Look up a lexeme by its identifier, Update the gloss on an existing lexeme entry
Not supported: Does not handle audio transcription, machine translation, or speech recognition — use for DLx language and lexeme record operations only.
The Digital Linguistics (DLx) REST API stores and serves linguistic field data — languages, lexemes, texts, and metadata — for researchers documenting and analysing the world's languages. Eighteen endpoints cover language records, lexeme entries, and the relationships between them, with simple header-based API key authentication. It is the canonical backend for DLx-compatible tools used in language documentation projects.
Patterns agents use DLx API for, with concrete tasks.
★ Field Linguistics Data Capture
Capture and store lexeme entries collected during language documentation field work. The /languages and /lexemes endpoints let researchers register a language and post lexeme records with transcription, gloss, and morphological metadata, building a structured corpus that other DLx-compatible tools can read. This replaces ad-hoc spreadsheets used by many documentation projects.
Register language with ISO code yuk, then post lexeme records for each entry collected in today's session with transcription and gloss
Cross-Tool Lexicon Sync
Synchronise a lexicon between desktop linguistic tools (FieldWorks, Toolbox) and the DLx web platform. The DLx REST API serves as a neutral hand-off point — desktop tools push entries via /lexemes and the web platform reads them back, so collaborators on different tools share one corpus of record.
Read lexemes for language id en-us-app, transform them to FieldWorks XML, and write them out to the desktop tool's project file
Public Language Resource Browser
Build a public browser over DLx-registered languages and their lexemes for educational and reference use. GET /languages lists languages and GET /languages/{languageID}/lexemes returns lexeme records, enabling a static-site generator to produce per-language pages without a live database.
For each registered language, fetch its lexeme list and generate a static HTML page listing transcriptions and glosses for public access
AI Agent Linguistic Research Assistant
An AI assistant supporting linguistic research can query DLx through Jentic to fetch language metadata or lexeme entries on demand. Searching for "list lexemes for a language" returns the matching DLx operation and its schema, so the agent can answer field-data questions without a custom integration.
When the researcher asks "what lexemes have we recorded for Yurok?", call /languages/{languageID}/lexemes with the Yurok language id and summarise the results
18 endpoints — the digital linguistics (dlx) rest api stores and serves linguistic field data — languages, lexemes, texts, and metadata — for researchers documenting and analysing the world's languages.
METHOD
PATH
DESCRIPTION
/languages
List registered languages
/languages/{languageID}
Retrieve a language record
/languages/{languageID}/lexemes
List lexemes for a language
/languages/{languageID}/lexemes/{lexemeID}
Retrieve a specific lexeme entry
/lexemes
List or search lexemes globally
/lexemes/{lexemeID}
Retrieve a lexeme by id
/languages
List registered languages
/languages/{languageID}
Retrieve a language record
/languages/{languageID}/lexemes
List lexemes for a language
/languages/{languageID}/lexemes/{lexemeID}
Retrieve a specific lexeme entry
/lexemes
List or search lexemes globally
Three things that make agents converge on Jentic-routed access.
Credential isolation
DLx API keys live encrypted in the Jentic vault. Agents receive a scoped execution token; the raw DLx key never enters the model context.
Intent-based discovery
Agents express research intent ("list lexemes for a language") and Jentic returns the matching DLx operation with its input schema.
Time to first call
Direct DLx integration: half a day for auth and pagination handling. Through Jentic: under 30 minutes.
Alternatives and complements available in the Jentic catalogue.
Wikimedia API
Encyclopedic and structured language metadata to enrich DLx language records
Use alongside DLx when an agent needs encyclopedic background or ISO code lookups for a language
Collins Dictionary API
General-purpose dictionary lookup rather than field-collected lexeme data
Choose Collins for major published languages; choose DLx for endangered or under-documented languages
OpenAI API
Generative AI to draft glosses or analyse lexeme patterns
Use when an agent needs to summarise patterns across DLx lexeme entries
Specific to using DLx API through Jentic.
What authentication does the DLx use?
DLx uses an API key passed in the Authorization header. Keys are issued by the DLx project for registered users. Through Jentic the key is held in the encrypted vault and injected at execution time only.
Can I retrieve all lexemes for a single language?
Yes. GET /languages/{languageID}/lexemes returns the lexeme records linked to that language record, paginated when the list is large. Each entry includes transcription, gloss, and morphological fields.
What are the rate limits for the DLx?
DLx is a research project and does not publish a fixed public rate limit. Polite use is expected; bulk imports should be batched and spaced out, and any 429 responses respected with backoff.
How do I list lexemes for a language through Jentic?
Run a Jentic search for "list lexemes for a language". Jentic returns GET /languages/{languageID}/lexemes with its path-parameter schema. Load it, supply the language id, and execute — no need to read the DLx spec.
Does the API support the full set of CRUD operations on lexemes?
The published spec exposes read access on languages and lexemes plus a small number of write paths for registered users. For destructive operations, project policy may require additional authorisation beyond the API key.
How do I install the Jentic SDK to call DLx?
Run pip install jentic, set JENTIC_AGENT_API_KEY to your ak_* key, then use Jentic with SearchRequest, LoadRequest, and ExecutionRequest. Sign up at https://app.jentic.com/sign-up.
/lexemes/{lexemeID}
Retrieve a lexeme by id