How to Use the Crowdin MCP in LlamaIndex

Q: Can LlamaIndex query Crowdin translation memories?

Yes, your agent uses listtranslationmemories to fetch segment counts and metadata. LlamaIndex stores this information as document nodes, making your translation history searchable via semantic queries.

Q: How does LlamaIndex handle Crowdin glossary terms?

The agent calls listglossaries to extract terminology pairs and IDs. LlamaIndex indexes these terms so your RAG pipeline can retrieve approved definitions during generation steps.

Q: Can I filter the tools available to my LlamaIndex agent in the MCP config?

Yes, you can use the allowedtools filter in the MCP tool spec. This lets you restrict the agent to specific tools like listprojectscreenshots if you only want it to index visual contexts.

Index Crowdin translation metadata via this MCP Server to power your LlamaIndex vector stores.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Crowdin MCP to LlamaIndex

Create your Vinkius account to connect Crowdin to LlamaIndex and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Crowdin with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Crowdin translation memories in LlamaIndex

The `list_translation_memories` tool lets your LlamaIndex RAG pipeline ingest segment counts and TM names directly into a vector index. Your agent queries this index to find reusable translations instead of calling external APIs repeatedly. This integration means your LlamaIndex agent answers queries about past translation work using actual, indexed TM segments. It queries the vector store to match new source strings against historical data retrieved by the MCP server.

Search Crowdin file structures with LlamaIndex

The `list_project_files` tool extracts file names, paths, and translation progress metrics for your LlamaIndex knowledge base. Your agent runs semantic searches over your project layout to locate missing translations instantly. You combine this file data with `get_file_details` to build an index of revision histories. When a user asks which files need updates, LlamaIndex queries the local index to pinpoint the exact file paths needing attention.

Analyze Crowdin project reports via LlamaIndex

The `list_project_reports` tool retrieves translation costs and progress reports directly into your LlamaIndex query engine. Your agent synthesizes this raw data to generate natural language summaries of your localization spend. By feeding report timestamps and types into your index, LlamaIndex tracks how your localization budget evolves. The agent compares these reports against `get_project_details` to verify if cost spikes correlate with new target languages.

Setup guide

Set up Crowdin MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Crowdin MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Crowdin tools.",
)
response = await agent.run("List recent Crowdin data")

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Crowdin. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Crowdin now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Crowdin MCP in LlamaIndex

Use llama-index-tools-mcp to load the tools into your LlamaIndex agent. The agent calls `list_project_files` and indexes the resulting file paths and progress metrics into your vector store.

Yes, your agent uses `list_translation_memories` to fetch segment counts and metadata. LlamaIndex stores this information as document nodes, making your translation history searchable via semantic queries.

The agent calls `list_glossaries` to extract terminology pairs and IDs. LlamaIndex indexes these terms so your RAG pipeline can retrieve approved definitions during generation steps.

Yes, you can use the allowed_tools filter in the MCP tool spec. This lets you restrict the agent to specific tools like `list_project_screenshots` if you only want it to index visual contexts.

Your localization file structures and project settings are processed in an ephemeral sandbox. Vinkius ensures that sensitive data retrieved via `get_project_details` never persists outside your configured LlamaIndex vector store.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript