> ## Documentation Index > Fetch the complete documentation index at: https://docs.textsetu.com/llms.txt > Use this file to discover all available pages before exploring further. # MCP Server > Connect Claude, Cursor, VS Code, and other MCP clients to your translations. TextSetu ships a **remote [Model Context Protocol](https://modelcontextprotocol.io) server** so AI agents — Claude, Cursor, VS Code Copilot, or any MCP-capable client — can manage your translations directly: read completeness stats, search keys, add and translate strings, import/export files, and work with branches, all in natural language. It's a thin layer over the [REST API](/api/introduction): every tool call goes through `/api/v1`, so the exact same authentication, scopes, permissions, and approval rules apply. Nothing the API won't let you do is reachable through MCP. * **Endpoint:** `https://api.textsetu.com/mcp` (self-host: `/mcp`) * **Transport:** Streamable HTTP * **Auth:** OAuth (approve in your browser) or a Bearer API token ## Connecting You don't need to paste a token. Connecting runs a standard **OAuth flow** — the first time a tool runs, TextSetu opens an **Authorize** screen in your browser; approve it and your client caches the token. (You can still use a token directly — see [Use a token instead](#use-a-token-instead).) ```bash theme={null} claude mcp add --transport http textsetu https://api.textsetu.com/mcp --scope user ``` Run any TextSetu tool and Claude Code walks you through the Authorize screen. Add to `~/.cursor/mcp.json` (global) or `.cursor/mcp.json` (per-project): ```json theme={null} { "mcpServers": { "textsetu": { "url": "https://api.textsetu.com/mcp" } } } ``` Add to `.vscode/mcp.json` (workspace) or your user `mcp.json`: ```json theme={null} { "servers": { "textsetu": { "type": "http", "url": "https://api.textsetu.com/mcp" } } } ``` Open **Settings → Connectors → Add custom connector**, set the URL to `https://api.textsetu.com/mcp`, and complete the Authorize prompt. (Remote connectors require a plan that supports them.) In **Settings → Connectors → Create** (enable **Developer mode** if prompted), add a custom connector with the MCP server URL `https://api.textsetu.com/mcp` and complete the Authorize prompt. Then attach the connector in the composer to use its tools. (Custom connectors require a paid plan and may need enabling by your workspace admin.) Any client that supports a **remote (HTTP)** MCP server works — point it at the endpoint: ```json theme={null} { "type": "http", "url": "https://api.textsetu.com/mcp" } ``` ### Use a token instead To skip the browser flow, present an API token on every request. In a JSON-configured client, add a `headers` object to the server entry from above: ```json theme={null} { "url": "https://api.textsetu.com/mcp", "headers": { "Authorization": "Bearer tsu_pat_…" } } ``` Claude Code takes the same thing as a flag on `claude mcp add`: ```bash theme={null} --header "Authorization: Bearer $TEXTSETU_TOKEN" ``` ## Authentication The MCP server accepts either TextSetu [token type](/api/introduction#authentication): | Token | Prefix | Project scope | | ------------------------- | ------------ | ------------------------------------------------------------------------------- | | **Personal Access Token** | `tsu_pat_…` | acts as you across every project you can access — pass `projectId` to each tool | | **Project token** | `tsu_proj_…` | bound to one project — `projectId` is optional and defaults to that project | When you connect through the browser **Authorize** flow, the consent screen lets you choose exactly this: a PAT (your full access) or a project-scoped token, and for the project token which **permissions** it may use (e.g. `translation_read`, `translation_create`), plus an optional expiry. Prefer the narrowest grant that does the job. Because every tool proxies to the REST API, all the usual rules hold: * **Writes** (`create_key`, `update_value`, `import_sources`, …) require the matching permission (e.g. `translation_create` / `translation_update`). * On a project whose **main branch is protected**, direct-to-main writes are rejected — target a branch (`branch` argument), then `merge_branch`. * When **approval is required**, non-approver edits land as proposals, exactly as they would over the API or in the app. ## Tools ### Translation memory & glossary The tools an agent reaches for *while translating* — reuse what was translated before, and honor the customer's terminology. | Tool | What it does | Key arguments | | --------------------- | ----------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------- | | `get_tm_matches` | Fuzzy TM matches with a match percentage. Call **before** translating so approved translations are reused | `projectId?`, `sourceTexts[]`, `languageCodes[]` | | `search_tm` | Concordance search — how a word or phrase was translated before, with full segments. Finds what whole-segment matching misses | `projectId?`, `query`, `languageCodes?`, `searchIn?`, `page?`, `limit?` | | `lookup_glossary` | Glossary terms occurring in the source, with translations and `doNotTranslate` / `usageStatus` flags | `projectId?`, `sourceTexts[]`, `languageCodes[]` | | `check_glossary` | Check a drafted translation for terminology issues. Call **after** drafting to self-review | `projectId?`, `sourceText`, `targetText`, `languageCode` | | `pretranslate` | Apply TM matches to untranslated strings in bulk (async) | `projectId?`, `minMatchPercentage?` | | `pretranslate_status` | Status of a pretranslate job | `projectId?`, `jobId` | Glossary and TM **management** tools operate on organization-level resources and therefore require a **PAT** (`tsu_pat_…`) — a project-scoped token is refused: | Tool | What it does | Key arguments | | ------------------------------- | ------------------------------------------ | ------------------------------------------------------------------------ | | `list_glossaries` | Glossaries in the org, with counts | `orgId` | | `list_glossary_terms` | Terms in a glossary (paginated) | `glossaryId`, `search?`, `page?`, `limit?` | | `create_glossary_term` | Add a term, optionally with translations | `glossaryId`, `term`, `translations?`, `doNotTranslate?`, `usageStatus?` | | `update_glossary_term` | Update a term's text, flags or notes | `glossaryId`, `termId`, … | | `set_glossary_term_translation` | Set a term's translation in one language | `glossaryId`, `termId`, `languageCode`, `value` | | `delete_glossary_term` | Delete a term | `glossaryId`, `termId` | | `list_translation_memories` | TMs in the org, with counts | `orgId` | | `list_tm_entries` | Entries in a TM (paginated) | `tmId`, `search?`, `page?`, `limit?` | | `create_tm_entry` | Add a source segment + translations | `tmId`, `sourceText`, `context?`, `translations?` | | `update_tm_entry` | Update an entry's source text or context | `tmId`, `entryId`, … | | `set_tm_entry_translation` | Set an entry's translation in one language | `tmId`, `entryId`, `languageCode`, `value` | | `delete_tm_entry` | Delete an entry | `tmId`, `entryId` | ### Translations, files & branches | Tool | What it does | Key arguments | | --------------------- | ------------------------------------------- | ------------------------------------------------------------------ | | `list_formats` | List supported file formats | — | | `get_stats` | Per-language completeness for a project | `projectId?`, `branch?` | | `list_languages` | List a project's languages | `projectId?` | | `list_keys` | List / search keys (paginated) | `projectId?`, `search?`, `page?`, `limit?`, `status?`, `branch?` | | `get_key` | Get a key with its values | `projectId?`, `keyId` | | `create_key` | Create a key, optionally with values | `projectId?`, `key`, `description?`, `tags?`, `values?`, `branch?` | | `update_value` | Set a value for a key in a language | `projectId?`, `keyId`, `lang`, `value`, `pluralForm?`, `branch?` | | `export_translations` | Export per-language files (base64) | `projectId?`, `format`, `languages?`, `status?`, `branch?` | | `import_sources` | Import source/translation files | `projectId?`, `format`, `files[]` | | `list_branches` | List a project's branches | `projectId?` | | `create_branch` | Create a branch (branching must be enabled) | `projectId?`, `name`, `description?` | | `merge_branch` | Detect conflicts, then merge into main | `projectId?`, `branchId` | `projectId` is optional only for a project-scoped token (it defaults to that token's project). With a PAT, pass it explicitly. `branch` targets an open translation branch instead of main. ### AI translation Draft translations with AI through the project's [AI engine](/docs/guides/ai-translation). Runs are asynchronous — start one, then poll for progress. | Tool | What it does | Key arguments | | --------------------- | -------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------- | | `ai_engine_info` | Report which AI engine a project uses and whether AI translation is available | `projectId?` | | `ai_translate` | Start an AI translation run (async) into chosen languages with candidate filters | `projectId?`, `targetLanguageCodes[]`, `onlyEmpty?`, `onlyOutdated?`, `includeTags?`, `excludeTags?`, `keyPrefix?`, `branch?`, `review?`, `batch?` | | `ai_translate_status` | Poll an AI translation run's progress and counts | `projectId?`, `jobId` | ## Example prompts Once connected, just ask — the agent picks the right tools: * *"How complete is the French translation for project ``?"* → `get_stats` * *"Find every key containing 'checkout' that's still in draft."* → `list_keys` * *"Add a key `cart.empty` with English 'Your cart is empty'."* → `create_key` * *"Translate `cart.empty` into German as 'Ihr Warenkorb ist leer'."* → `update_value` * *"Export the approved French and German translations as nested JSON."* → `export_translations` * *"Create a branch `feature/checkout` and merge it once it's clean."* → `create_branch` / `merge_branch` With translation memory and glossary, the agent can translate *the way you already do*: * *"Translate these new strings into French — reuse anything we've translated before and follow our glossary."* → `get_tm_matches` + `lookup_glossary`, then `update_value` * *"How have we translated 'checkout' before?"* → `search_tm` * *"Review my French translation of this string for terminology problems."* → `check_glossary` * *"Fill in every French string that has a 90%+ match in the TM."* → `pretranslate` * *"Add 'invoice' to the glossary as 'facture' in French."* → `create_glossary_term` ## Notes * **Rate limit:** 120 requests/min per IP on the MCP endpoint (separate from the REST API's per-token limit). * **Sessions** are stateful (Streamable HTTP) and idle sessions are evicted after 30 minutes — your client re-initializes transparently. * The server exposes standard MCP discovery, so OAuth-capable clients configure themselves; see the [API Reference](/api/introduction) for the underlying endpoints.