How to Use the Weblate MCP in CrewAI

Q: Can I audit user roles with CrewAI and Weblate?

Yes. You use the listroles tool to get all current roles for a specific user, allowing your crew to build a complete profile of their permissions across Weblate.

Q: What is the workflow when creating new languages with CrewAI?

The process flows from listlanguages (discovery) to getlanguage (verification). The crew validates that the language definition exists and then proceeds with subsequent actions.

Coordinate specialized localization agents with CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Weblate MCP to CrewAI

Create your Vinkius account to connect Weblate to CrewAI 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 Weblate with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Discover Projects with MCP Server

Use `list_projects` and `list_groups` to gather all active projects and defined groups. Agent A (Researcher) pulls this list, and then Agent B (Analyzer) iterates through the results to identify missing components. The shared memory allows the whole crew to hold the complete inventory of assets found during discovery, preventing redundant checks.

Manage Permissions with CrewAI

Agent C (Enforcer) uses `create_role` and `get_role` to audit current permissions. If a role is missing necessary rights, the agent can create it and then assign it via `add_group_roles`. This hierarchical execution model ensures that permission changes only happen after the required roles are verified and created.

Audit User Contributions with CrewAI

The crew runs specialized audits: Agent A calls `list_user_notifications` to see what a user is subscribed to. Then, Agent B uses `get_user_contributions` to analyze the actual translation volume. This separation of duties means one agent handles communication status while another focuses purely on contribution metrics.

Setup guide

Set up Weblate MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Weblate tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Weblate Analyst",
    goal="Access and analyze Weblate data via MCP.",
    backstory="Expert analyst with direct Weblate access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Weblate transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Weblate Analyst",
        goal="Access and analyze Weblate data via MCP.",
        backstory="Expert analyst with direct Weblate access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Weblate transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 Weblate. 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 Weblate 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 Weblate MCP in CrewAI

The crew runs a sequence: first, listing all projects using `list_projects`. Then, specialized agents can independently call tools like `get_project` or `get_group` on each project ID found.

Yes. You use the `list_roles` tool to get all current roles for a specific user, allowing your crew to build a complete profile of their permissions across Weblate.

The process flows from `list_languages` (discovery) to `get_language` (verification). The crew validates that the language definition exists and then proceeds with subsequent actions.

It supports complex tasks. For instance, one agent monitors the `get_project_repository` status while another automatically triggers a cleanup operation if outdated files are detected.

The server accesses user IDs, project metadata, language definitions, and contribution statistics. It manages structured organizational data about the localization process but doesn't store the raw text translations.

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