Integration

Lexeri integration

Lexeri is a terminology management platform (by Lexeri GmbH, Hamburg) that keeps brand wording and technical terms consistent across languages. With the API you can check a text against the termbase and get the preferred replacement for each term that should not be used, search and read terms with their term entries, definitions and version history, create, change and delete terms (published at once, no review step), manage usage examples, list and create topics, read the termbase's languages and custom fields, and export the termbase as TBX, Excel or CSV for CAT and translation tools. Terms and versions name the users who created them (name and email). Authentication: an API token created in the termbase settings (tab API) and sent as a Bearer token; it belongs to one termbase, acts with its user's permissions and carries scopes (show and read always; edit_terms, edit_term_entries, export_termbase and check_text as chosen).

Connect Lexeri How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Lexeri.Built from the 16 Lexeri tools below, on the connection you add once.

What you can do with Lexeri

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Each badge shows the default agent permission of an endpoint (allowed: an agent calls it without asking; ask first: you are asked before an agent calls it, when the agent or chat asks permission for sensitive actions; never: no agent may call it), which every user can change endpoint by endpoint in their credential settings.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Term, 5 operations

create_termCreate termPOSTAgents: ask firstCreates a term and publishes it at once in the shared termbase (no review step). Without term_entry_id it starts a new term entry; with it, the term joins that entry as a synonym or translation. Always send state.
delete_termDelete termDELETEAgents: ask firstPermanently deletes a term. Deleting the last term of a term entry deletes the whole entry with its definitions, notes and images. Needs the edit_terms scope.
get_termGet termGETAgents: ask firstReturns one term in full: grammar, usage, state, custom fields, creator, its term entry with definitions, topics, tags and preferred terms in all languages, its sources, and termbase (whose identifier the termbase tools need).
list_termsList termsGETAgents: ask firstSearches the published terms of the termbase (search, language, usage state, type, tag, topic, missing translations, last change) and returns one page, 500 per page by default. Add fields to get each term's preferred_term or term_entry.
update_termUpdate termPATCHAgents: ask firstChanges the attributes of a term you send; the others stay. Published at once and recorded as a new version. fields REPLACES all custom field values of the term: read them with get_term and send the ones to keep.

Export, 3 operations

create_exportCreate exportPOSTAgents: ask firstExports the termbase to a file (TBX, Excel, CSV for memoQ or DeepL, or images ZIP), optionally filtered; download_url then leads to the file for one hour. Waits for the job and returns the finished result; gives up after 10 minutes.
get_exportGet exportGETAgents: ask firstReturns an export with its state (new, running, finished, failed). Once finished, download_url leads to the file and is valid for one hour from this answer; call again for a fresh link.
list_exportsList exportsGETAgents: ask firstLists the exports of the termbase still stored, with type, state (new, running, finished, failed), filters, file name and download link once finished. Exports are deleted two months after creation (scheduled ones after three days).

Usage example, 3 operations

create_usage_exampleCreate usage examplePOSTAgents: ask firstAdds a usage example sentence to a term, visible at once to everyone using the termbase. Needs the edit_terms scope.
delete_usage_exampleDelete usage exampleDELETEAgents: ask firstPermanently deletes a usage example from a term. Needs the edit_terms scope.
list_usage_examplesList usage examplesGETAgents: ask firstLists the usage examples of a term: sentences showing how the term is used, or must not be used, with their source and the user who added them (name and email, personal data).

Topic, 2 operations

create_topicCreate topicPOSTAgents: ask firstCreates a topic in the termbase, at the top level or below parent_topic_identifier, with its title and description in one language. Visible at once to the termbase's users. Needs the edit_term_entries scope.
list_topicsList topicsGETAgents: ask firstLists all topics of the termbase, nested ones included, sorted by title, with titles and descriptions per language. fields adds term counts, ancestors and children.

Live, 1 operation

check_textCheck textPOSTAgents: ask firstChecks a short text (about a paragraph) against the termbase: each match gives the term found and, when it should not be used, preferred_term to use instead, with phrases, sentences and misspellings. Reads only.

Termbase, 1 operation

get_termbaseGet termbaseGETAgents: ask firstReturns the token's termbase: name, languages, number of terms, tags, custom field definitions of term entries and terms, custom usage states, all topics and the subscription. Pass the termbase identifier (termbase.identifier in get_term).

Version, 1 operation

list_term_versionsList term versionsGETAgents: ask firstReturns every version of a term, newest first and the current one included. Each version's changelog lists the changed attributes (old and new value); creator names who made the change (personal data).

Use Lexeri from Claude Code, Cursor or Codex

Connect Lexeri in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Lexeri operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Lexeri

Create your workspace
Sign up free. Nothing to install.
Connect Lexeri once
Add your Lexeri connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.