Connect your AI Agents to Straker in minutes

What is a Straker MCP?

A Straker MCP is an MCP server that connects your agents to Straker's translation platform via tools. Your agents can invoke these tools to submit text and files for translation, track job status, approve quotes, and retrieve completed translations, and more.

Straker doesn't offer its own official MCP server, but you can use one from a third-party platform, like Merge Agent Handler.

How can I use the Straker MCP server?

The use cases naturally depend on the agent you've built, but here are a few common ones:

• Automated content translation: When a product description or marketing asset is updated in a CMS, an agent submits the new content to Straker for translation into all configured target languages, removing the need for manual submission each time

• File localization pipeline: An agent picks up XLIFF or JSON localization files from a code repository, submits them to Straker, polls for completion, and writes the translated files back once the job finishes

• Quote review and approval: An agent generates a translation quote for a batch of documents, compares the estimated cost against a budget threshold, and either auto-approves or routes the quote to a human for review

• Multi-language knowledge base publishing: When a support article is published in English, an agent submits it to Straker and updates the localized versions in the knowledge base once each translation job completes

What are popular tools for Straker's MCP server?

Here are some of the most commonly used tools:

• translate_text: submits a string of text to Straker for translation and returns a job key for tracking. Use this when an agent needs to translate short-form content like UI strings, product titles, or notification copy

• translate_file: submits a file (XML, XLIFF, JSON, or DOCX) for translation and returns a job key. Good for workflows that process structured localization files or long-form documents as part of a content pipeline

• get_translation: retrieves the current status and results of a translation job by job key. Call this when an agent needs to poll for completion before writing translated content to a downstream system

• approve_quote: approves a translation quote by TJ number for jobs in a quoted status. Helpful when an agent evaluates quote cost against a threshold and needs to confirm the job to move it into processing

• cancel_translation: cancels a queued translation job before it begins processing. Use this when an agent detects that source content was updated after submission and needs to restart the job with the correct version

• list_languages: returns all language codes supported by Straker. Call this when an agent needs to validate a target language before submitting a job or build a dynamic language selection step into a workflow

What makes Merge Agent Handler's Straker MCP server better than alternative Straker MCP servers?

Here is why Merge Agent Handler's Straker MCP server is the right choice over building or using an alternative:

• Enterprise-grade security and DLP: Merge Agent Handler includes built-in data loss prevention controls that let you block or redact sensitive fields before they reach an agent. For Straker, this means you can prevent proprietary source content, confidential documents, and account-level custom field data from being exposed even when the agent has broad access

• Managed authentication and credentials: Merge stores and refreshes Straker credentials on your behalf. You never expose raw API keys to an agent or handle credential rotation across environments manually

• Real-time observability and audit trail: Every tool call made against Straker is logged with timestamp, tool name, input parameters, and response metadata. You can track exactly which content was submitted, when, and what the job result was without instrumenting anything yourself

• Tool Packs and controlled access: Tool Packs let you bundle specific Straker tools with tools from other connectors into a single MCP endpoint, scoped to a specific use case. An agent handling file localization doesn't need access to quote approval tools

How can I start using Merge Agent Handler's Straker MCP server?

You can take the following steps:

1. Create or log into your Merge Agent Handler account and navigate to Tool Packs (collections of connector tools scoped to a specific use case).

2. Create a new Tool Pack, then find and enable the Straker connector. Choose which tools to include: enable read and status tools for monitoring workflows, or add submission and approval tools if your agent needs to create and manage translation jobs end to end.

3. Add a Registered User inside the Tool Pack. This is the identity context under which your agent operates. Merge generates a unique MCP URL scoped to this user once it's created.

4. From the Registered User detail page, authenticate Straker by completing the credential flow. Merge stores and manages the credentials going forward.

5. Copy the MCP URL from the Tool Pack detail page and generate an API key from Settings. You'll need both to connect your agent.

6. Add the MCP server to your agent or IDE using the MCP URL and API key. Your Straker tools are now accessible through that endpoint.