> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.ada.cx/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.ada.cx/_mcp/server.

# list_glossary_terms

Lists the AI agent's configured glossary terms. The glossary maps colloquial **user terms** an end user might say to the canonical **AI agent terms** the agent should use, optionally per language, plus an optional business definition. Use it to review the glossary or to detect conflicts between it and the rest of the configuration. For a full step-by-step conflict audit, call [`get_glossary_conflict_guide`](/mcp/tools/get-glossary-conflict-guide) first.

## Example prompts

* "List the terms in our glossary."
* "What does our Agent translate `UDMP` to?"
* "Show me every glossary term and its definition."

## Parameters

| Parameter | Type   | Required | Description                                                                                          |
| --------- | ------ | -------- | ---------------------------------------------------------------------------------------------------- |
| `cursor`  | string | No       | Opaque pagination cursor returned as `next_cursor` by a previous call. Omit to fetch the first page. |
| `limit`   | number | No       | Maximum number of terms to return. Default 50, max 100.                                              |

## Pagination

Results are paginated. When the response includes a non-null `next_cursor`, pass it back as `cursor` on the next call to fetch the following page; repeat until `next_cursor` is `null` to retrieve the full glossary.

## Response

Returns `glossary_terms` (the page of terms), `returned_count`, and `next_cursor`. Each term includes:

* **`id`** — Ada's internal identifier for the term, stable within the client.
* **`external_id`** — Client-provided identifier, unique within the client's glossary.
* **`translation_mode`** — `custom` (the `user_terms` trigger the matching `ai_agent_terms`) or `default` (matched only to surface the term's definition).
* **`user_terms`** — Colloquial terms, per language, the agent detects in a user message. A language can hold several terms (aliases), all mapping to that language's single AI agent term.
* **`ai_agent_terms`** — Canonical terms, per language, the agent should use instead.
* **`definition`** — Optional business definition of the term.
* **`voice_detection_enabled`** — Whether the term is passed to the voice agent as a key term. Only present when the AI Agent has the Voice channel configured; omitted otherwise.
* **`availability_rules`** — The availability rule restricting which end users the term applies to, or `null` when the term is unconditional.

The response also includes a `field_descriptions` block documenting each field inline.

> **Tip**
>
> To check whether any term contradicts your custom instructions, company description, coaching, or knowledge, use [`get_glossary_conflict_guide`](/mcp/tools/get-glossary-conflict-guide) — it walks the assistant through cross-referencing the glossary against the rest of your configuration.