Connect Crowdin to Microsoft Copilot via MCP

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Crowdin, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

Crowdin + Microsoft Copilot

Crowdin localization on crowdin.com and Crowdin Enterprise through API v2: projects and progress per language, files, source strings, translations and approvals, comments and issues, tasks, reports, translation builds and exports, translation memories, glossaries and project members.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

CROWDIN_PERSONAL_ACCESS_TOKEN, CROWDIN_API_HOST

Step 1 — Get credentials

Setting up takes about 2 minutes. You need a crowdin.com or Crowdin Enterprise account.

1. Create a personal access token. On crowdin.com: Account Settings > API > New Token. On Crowdin Enterprise: profile > Settings > API > New Token inside your organization.
2. Pick the scopes you need: Projects, Source files and strings, Translations, Tasks, Reports, Translation memory, Glossaries. Read-only scopes give a read-only setup. Copy the token: it is shown only once.
3. Paste it into CROWDIN_PERSONAL_ACCESS_TOKEN; it is sent as Authorization: Bearer <token>.
4. CROWDIN_API_HOST: api.crowdin.com for crowdin.com, or <organization>.api.crowdin.com for Enterprise, with the organization from your Enterprise URL https://<organization>.crowdin.com.
5. Install the connector and run crowdin_get_authenticated_user: it shows the user the token belongs to and confirms token and host.

Crowdin's own MCP server: Crowdin also runs an official MCP server (https://mcp.crowdin.com/v2/mcp, on Enterprise https://<organization>.mcp.crowdin.com/v2/mcp, with the personal access token as Bearer). This connector works with the API v2 directly.

What it reads:

• Projects with source and target languages, type (file-based or string-based) and settings such as workflow, QA checks, machine translation and translation memory; progress per language for the project or one file; every supported language with its Crowdin id.
• Branches, directories and source files, plus a short-lived link to the source version of a file (crowdin_download_file).
• Source strings with key, text, context, max length, labels and plural forms, filtered by file, branch, directory, label, task, a text match or a CroQL expression.
• Translations (suggestions) into one language at a time with author and rating, and the approvals with approver and time.
• Comments and issues on strings, for example unresolved requests for context.
• Tasks with type, status, language, assignees, progress and deadline; project members with role and languages.
• Translation memories and their segments, a concordance search (crowdin_search_tm) for how a phrase was translated before, glossaries and their terms.

What it writes:

• crowdin_add_string adds a source string to a file (file-based projects). crowdin_edit_string changes it with JSON Patch on /text, /identifier, /context, /isHidden, /maxLength or /labelIds; update_option decides what happens to existing translations when the text changes.
• crowdin_add_translation adds a suggestion; crowdin_approve_translation approves it, so it goes into the exported files (this needs proofreader rights for that language).
• crowdin_add_comment comments on a string or reports an issue: a question, a translation or source mistake, a request for context.
• crowdin_create_task creates a translate or proofread task for files (or strings in string-based projects) in one language, with assignees and a deadline; on Enterprise it takes workflow_step_id instead of type. crowdin_edit_task changes it with JSON Patch, for example /status to done.
• crowdin_add_tm_segment adds the same sentence in several languages to a translation memory; crowdin_add_glossary_term adds a term, optionally as the translation of an existing term or into a concept.

Reports and translated files: reports run in the background. crowdin_generate_report returns data.identifier; the AI polls crowdin_get_report_status until status is finished and then fetches the link with crowdin_download_report. crowdin_export_project_translation exports one language as one file right away. crowdin_build_project_translations builds every file and language as a zip: the AI polls crowdin_get_build_status, then calls crowdin_download_build. Download links expire after a short time (expireIn), so the AI hands them to you instead of keeping them. These calls are POSTs but do not change the content.

Nothing is switched off at install: there are no delete tools.

Ids and formats: project, file, string, translation, task and user ids are numbers; report identifiers are strings. Languages use Crowdin ids such as de, fr, es-ES, pt-BR or zh-CN. Times are ISO 8601 with offset. PATCH tools take JSON Patch lists: [{"op": "replace", "path": "/status", "value": "done"}]. Lists come as {"data": [{"data": {...}}, ...], "pagination": {"offset": 0, "limit": 25}}, single items as {"data": {...}}. Progress is counted in words and phrases, with translationProgress and approvalProgress in percent.

Paging: limit (25 by default, at most 500) and offset. When a page holds limit items, the AI asks for the next one with offset + limit.

Limits: 20 simultaneous requests per account, across all its tokens, on crowdin.com and Enterprise; 429 means wait.

Common errors: 401 means a wrong or expired token, or the wrong host. 403 means a token without the scope, or an account without rights in the project. 404 means an unknown id. 400 and 422 are validation errors naming the field.

The connector does not delete projects, files, strings or translations, and does not upload source files.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in Microsoft Copilot

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Microsoft Copilot uses MCP servers through agents built in Copilot Studio: you add AnythingMCP to an agent as a tool, then publish the agent to Microsoft 365 Copilot and Teams. Copilot Studio connects from Microsoft's cloud over Streamable HTTP, which AnythingMCP supports.

1. In Copilot Studio, open your agent (or create one), go to Tools and choose Add a tool → New tool → Model Context Protocol.
2. Enter a Server name (for example AnythingMCP), a Server description that says what the connector does, and the Server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID. Copilot Studio uses the description to decide when to call the server.
3. Under authentication, choose API key, set Type to Header and the header name to X-API-Key, then select Create.
4. In Add tool, choose Create a new connection, paste an MCP API key from AnythingMCP (MCP Servers → your server → API keys) and select Add to agent.
5. Try it in the agent's Test pane: ask for something that needs the Crowdin tools.
6. Select Publish, then Channels → Microsoft 365 and Microsoft Teams, keep Make agent available in Microsoft Copilot selected and choose Add channel. See agent in Teams installs it for you; in Microsoft 365 Copilot, type @ and pick the agent.

Prefer per-user sign-in? Choose OAuth 2.0 → Dynamic discovery instead of an API key: each user then signs in to AnythingMCP the first time the agent calls it.

Self-hosting? Use your instance's public HTTPS address instead of https://cloud.anythingmcp.com. Copilot Studio connects from Microsoft's cloud, so localhost does not work.

Available tools

Example prompts

• "How far along are the German and Japanese translations of our app project, translated and approved?"
• "Which strings in the checkout file have open issues asking for context?"
• "How did we translate "Sign in" into French before? Search the translation memory."
• "Create a proofreading task for the Spanish translation of the onboarding file, due Friday, and assign it to Maria."
• "Build the translated files for all languages, approved translations only, and give me the zip link."

FAQ

Which Copilot is this for? Microsoft 365 Copilot at work, through agents built in Copilot Studio. The Microsoft Copilot app for personal accounts has no option to add your own MCP server.

What do I need? A work account with access to Copilot Studio (a license or a trial) to build the agent. People who use it in Microsoft 365 Copilot or Teams need access to the agent: share it with them, or ask an admin to publish it to the organization. If your organization applies data policies to Power Platform connectors, they cover MCP servers too.

The agent doesn't call the tools. Check that the header name is exactly X-API-Key and that the key belongs to the same MCP server as the URL, and make the server description specific: Copilot Studio uses it to decide when to call the server. Publish the agent again after each change; in an open chat, type "start over" to get the new version.

Next steps

• Connector landing page
• Connect to Claude
• Connect to ChatGPT
• Connect to Cursor
• Connect to Gemini
• Connect to Meta Muse