Smartling MCP connector for AI agents

Tools your localization agent reaches for on Smartling MCP, scoped per user.

CALL ANY TOOL

Manage translation jobs, strings, glossaries, and issues in Smartling with the signed-in user's OAuth 2.1 token.

smartlingmcp_smartling_get_available_accounts_for_current_user

Get available accounts

List the Smartling translation accounts the signed-in user can access.

Parameters

Name

Type

Required

Description

—

No parameters required

smartlingmcp_smartling_get_project

Get project

smartlingmcp_smartling_list_projects

List projects

smartlingmcp_smartling_get_job

Get job

smartlingmcp_smartling_list_jobs

List jobs

smartlingmcp_smartling_create_job

Create job

smartlingmcp_smartling_update_job

Update job

smartlingmcp_smartling_get_job_history

Get job history

smartlingmcp_smartling_authorize_job

Authorize job

smartlingmcp_smartling_add_strings_to_job

Add strings to job

smartlingmcp_smartling_remove_strings_from_job

Remove strings from job

smartlingmcp_smartling_list_file_jobs

List file jobs

smartlingmcp_smartling_create_strings

Create strings

smartlingmcp_smartling_search_strings

Search strings

smartlingmcp_smartling_add_tags_to_strings

Add tags to strings

smartlingmcp_smartling_remove_tags_from_strings

Remove tags from strings

smartlingmcp_smartling_remove_all_tags_from_strings

Remove all tags from strings

smartlingmcp_smartling_request_upload_url

Request upload URL

smartlingmcp_smartling_machine_translate_text

Machine translate text

smartlingmcp_smartling_machine_translate_file

Machine translate file

smartlingmcp_smartling_get_word_count_report

Get word count report

smartlingmcp_smartling_export_glossary

Export glossary

smartlingmcp_smartling_get_glossary

Get glossary

smartlingmcp_smartling_list_glossaries

List glossaries

smartlingmcp_smartling_match_glossary_terms

Match glossary terms

smartlingmcp_smartling_search_translation_memory

Search translation memory

smartlingmcp_smartling_get_styleguide

Get styleguide

smartlingmcp_smartling_list_styleguides

List styleguides

smartlingmcp_smartling_get_linguistic_package

Get linguistic package

smartlingmcp_smartling_list_linguistic_packages

List linguistic packages

smartlingmcp_smartling_get_workflow_step_types

Get workflow step types

smartlingmcp_smartling_list_workflows

List workflows

smartlingmcp_smartling_list_users

List users

smartlingmcp_smartling_list_content_assignments

List content assignments

smartlingmcp_smartling_create_issue

Create issue

smartlingmcp_smartling_get_issue

Get issue

smartlingmcp_smartling_edit_issue_text

Edit issue text

smartlingmcp_smartling_open_or_close_issue

Open or close issue

smartlingmcp_smartling_update_issue_type

Update issue type

smartlingmcp_smartling_update_issue_severity_level

Update issue severity

smartlingmcp_smartling_update_issue_assignee

Update issue assignee

smartlingmcp_smartling_delete_issue_assignee

Delete issue assignee

smartlingmcp_smartling_update_issue_answered

Update issue answered state

smartlingmcp_smartling_add_issue_comment

Add issue comment

smartlingmcp_smartling_get_issue_comment

Get issue comment

smartlingmcp_smartling_list_issue_comments

List issue comments

smartlingmcp_smartling_update_issue_comment

Update issue comment

smartlingmcp_smartling_delete_issue_comment

Delete issue comment

smartlingmcp_smartling_find_account_issues

Find account issues

smartlingmcp_smartling_find_project_issues

Find project issues

smartlingmcp_smartling_count_account_issues

Count account issues

smartlingmcp_smartling_count_project_issues

Count project issues

smartlingmcp_smartling_execute_lqa_evaluation

Run LQA evaluation

Build your Agent

Same OAuth 2.1 vault and scoped tool list across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
const sk = new ScalekitClient(
  process.env.SCALEKIT_ENVIRONMENT_URL,
  process.env.SCALEKIT_CLIENT_ID,
  process.env.SCALEKIT_CLIENT_SECRET,
);
const page = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["smartlingmcp"], toolNames: [
    "smartlingmcp_smartling_search_strings",
    "smartlingmcp_smartling_list_jobs",
    "smartlingmcp_smartling_get_project",
  ]}, pageSize: 100,
});

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";
const sk = new ScalekitClient(
  process.env.SCALEKIT_ENVIRONMENT_URL,
  process.env.SCALEKIT_CLIENT_ID,
  process.env.SCALEKIT_CLIENT_SECRET,
);
const page = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["smartlingmcp"], toolNames: [
    "smartlingmcp_smartling_search_strings",
    "smartlingmcp_smartling_list_jobs",
    "smartlingmcp_smartling_get_project",
  ]}, pageSize: 100,
});
const openai = new OpenAI();

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";
const sk = new ScalekitClient(
  process.env.SCALEKIT_ENVIRONMENT_URL,
  process.env.SCALEKIT_CLIENT_ID,
  process.env.SCALEKIT_CLIENT_SECRET,
);
const page = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["smartlingmcp"], toolNames: [
    "smartlingmcp_smartling_search_strings",
    "smartlingmcp_smartling_list_jobs",
    "smartlingmcp_smartling_get_project",
  ]}, pageSize: 100,
});
const anthropic = new Anthropic();

import { ScalekitClient } from "@scalekit-sdk/node";
const sk = new ScalekitClient(
  process.env.SCALEKIT_ENVIRONMENT_URL,
  process.env.SCALEKIT_CLIENT_ID,
  process.env.SCALEKIT_CLIENT_SECRET,
);
const page = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["smartlingmcp"], toolNames: [
    "smartlingmcp_smartling_search_strings",
    "smartlingmcp_smartling_list_jobs",
    "smartlingmcp_smartling_get_project",
  ]}, pageSize: 100,
});

Try these prompts

Copy a prompt into your agent. Each one maps to Smartling translation tools for the signed-in user.

Jobs and strings

Copy the prompt

Copied

List every job due this week in the acme-web project.

Copy the prompt

Copied

Add these 20 strings to the LOC-Q3 job and authorize it.

Copy the prompt

Copied

Which strings are missing a Spanish translation?

Glossary and quality

Copy the prompt

Copied

Check this paragraph against our glossary before it goes to translators.

Copy the prompt

Copied

Search translation memory for a match on this exact sentence.

Copy the prompt

Copied

Run an LQA evaluation on the latest German job.

Issues and reporting

Copy the prompt

Copied

Open an issue on this string flagging a tone mismatch.

Copy the prompt

Copied

List unresolved issues across the account.

Copy the prompt

Copied

Get the word count report for the file we just uploaded.

SEE HOW AUTH WORKS

Your users connect once. Their Smartling OAuth 2.1 tokens stay vaulted, every call is checked, and every action is logged.

Authorize

Your user connects

Smartling MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Smartling MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Smartling MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Smartling MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

Reuse the same per-user OAuth 2.1 vault and audit chain on other localization and content connectors.

No items found.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Smartling key makes every job authorization and string edit look like a bot. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared key
audit → bot_acct

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Smartling MCP today. Others tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Smartling MCP as the user or a shared key?

Per-user resolution. Each tool call uses the signed-in user's Smartling OAuth 2.1 token, so job, string, and glossary calls attribute to that user in the audit log.

Where is the Smartling token stored?

In Scalekit's AES-256 vault, namespaced per tenant. Tokens refresh automatically. You revoke access from one dashboard without rotating a shared secret across every agent.

Can I limit what the agent does in Smartling MCP?

Yes. Filter tool names in listScopedTools (for example smartlingmcp_smartling_search_strings only) and Scalekit checks that scope before the API call.

What happens when a user revokes access?

The next Smartling tool call fails closed for that user. Other users and other connectors are unaffected. The revoke is logged.

Can the agent authorize jobs or edit strings on my behalf?

Only within the scoped tools you grant. Authorizing a job or editing a string uses the signed-in user's own Smartling permissions, so the agent can never do more than that user could.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit