Agents Index

Transept

OnlineNew

Translate documents with glossaries, style guides and translation memory; run and read back jobs.

Visit publisherConnectJSON

What it can do: 42 tools

  • me_getThe account this API key belongs to, the key in use, its scopes, and the credit balance available to spend.
  • project_listList projects you can file documents into.
  • project_createCreate a project (pass team_id for a team project; parent_id for a sub-project of a top-level project — same owner, one level deep).
  • document_listList documents, newest first. One row per language version; siblings share language_group_id.
  • document_getDocument metadata + its language group.
  • document_createCreate a document from inline text/markdown/html and fan out target languages.
  • document_updateUpdate document metadata (title / category / project filing).
  • document_deleteDelete ONE language version of a document.
  • document_add_languagesAdd target-language sibling versions to a document (grows its language group). Idempotent — languages already in the group are skipped.
  • document_content_getRead content as json | markdown | html | strings (binary formats: use the REST content endpoint).
  • document_attach_resourcesAttach/detach glossaries + style-guide versions ([] = detach all of that kind).
  • document_resync_sourceRe-parse the document from its STORED source file and re-align blocks (unchanged blocks keep translations). The file owns sources: block_update edits are NOT in the file, so a resync overwrites them — resync when the sou
  • strings_importImport a Transept Strings corpus (.tstrings.json shape). Locales: explicit params win; with none named the corpus header target_locales apply (no locales anywhere → sync no_target_languages). A single-locale import is ON
  • strings_reimportRe-submit the WHOLE current corpus against an existing master: the server diffs by unit id and answers with {units, versions[], delta_block_ids} — pass delta_block_ids VERBATIM as group_run_start.block_ids to run only th
  • block_updateEdit a block's SOURCE content (Slate JSON). Note: edits live on the block, not in the stored source file — a later document_resync_source re-parses the file and overwrites them.
  • block_translation_updateEdit a translation (Slate JSON); it stays active and feeds TM.
  • processing_job_getPoll an import job — the id returned by strings_import (or a REST file upload / Figma import). Runs are NOT processing jobs: poll those with run_get.
  • workflow_listSaved workflows (ids go into run_start.workflow_id).
  • workflow_template_listBuilt-in templates (ids go into run_start.template_id).
  • run_estimatePrice a run (free, no side effects). Costs are in credits.
  • run_startStart a workflow run. BILLS CREDITS — without confirm:true this only returns the estimate and starts nothing.
  • run_getPoll a run: status, progress, and (when gate_pending) the review-gate digest.
  • run_listList runs, newest first. Paged like document_list: {data, has_more, next_cursor}.
  • run_cancelCancel a run (idempotent — answers with the resulting status, so an already-terminal run reads as what it already was).
  • run_gate_approveApprove a review gate. Continuing downstream steps BILLS CREDITS — without confirm:true this only returns what continuing will cost (up to max_credits) and continues nothing. Omit block_ids to continue over ALL blocks th
  • run_gate_acknowledgeDismiss a review gate without continuing.
  • group_run_estimatePrice a multi-language fan-out (free).
  • group_run_startRun a workflow across many languages. BILLS CREDITS — without confirm:true this only returns the estimate.
  • group_run_getPoll a group run: rollup + per-language lanes.
  • group_run_listList group runs, newest first.
  • group_run_cancelCancel every still-active lane of a group run.
  • glossary_listList glossaries (yours + your teams’).
  • glossary_getOne glossary with its terms.
  • glossary_createCreate a glossary (optionally seed terms).
  • glossary_terms_addAdd terms in bulk; the answer is counts.
  • styleguide_listList style guides with their ACTIVE version id (what documents consume).
  • styleguide_getOne style guide incl. the active version content.
  • tm_queryQuery translation memory (hybrid retrieval; free).
  • tm_importImport a TMX/XLIFF file’s text into translation memory (free; async embeddings).
  • webhook_listList outgoing webhook endpoints (no secrets).

…and 2 more.

Connect it

Claude Code
claude mcp add --transport http transept https://app.transept.ai/api/public/v1/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://app.transept.ai/api/public/v1/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "transept": {
      "url": "https://app.transept.ai/api/public/v1/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "transept": {
      "type": "http",
      "url": "https://app.transept.ai/api/public/v1/mcp"
    }
  }
}

Questions

What does Transept do?

Translate documents with glossaries, style guides and translation memory; run and read back jobs. It exposes 42 tools to AI assistants.

What tools does Transept provide?

42 tools, including me_get, project_list, project_create, document_list, document_get, document_create, document_update, document_delete, document_add_languages, document_content_get, document_attach_resources, document_resync_source….

How do I connect Transept to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://app.transept.ai/api/public/v1/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does Transept require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is Transept online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes Transept?

transept.ai. The official MCP Registry verified that the publisher controls this domain before accepting the listing.

Similar in Productivity & Docs