How to Use the AB.GL MCP in CrewAI

Q: How do I add AB.GL tools to my CrewAI agents?

Install crewaitools via pip. You pass the Vinkius MCP endpoint URL directly into the mcps array when defining your agent.

Q: Can I restrict which AB.GL tools a specific CrewAI agent uses?

You handle that via the MCPServerHTTP class. Apply a toolfilter to ensure your analysis agent only accesses getlinkstats while your execution agent handles creation.

Deploy autonomous multi-agent teams in CrewAI to manage your short links and track click stats.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AB.GL MCP to CrewAI

Create your Vinkius account to connect AB.GL 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 AB.GL with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

CrewAI Campaign Management

The `create_short_link` tool allows your marketing agent to generate tracking URLs for new content automatically through the MCP Server. A secondary agent takes those links and distributes them across your social platforms. Modifying active campaigns requires zero human input. When a destination URL changes, your moderator agent uses `update_link` to redirect traffic instantly. Old campaigns get pruned by a cleanup agent calling `delete_link`.

Delegated Traffic Analysis

The `get_link_stats` tool equips your data analysis agent with real-time click metrics. It pulls the performance numbers from the MCP connection and hands them off to a reporting agent for formatting. Account-wide audits run on a schedule using `list_links`. The primary agent delegates the data gathering to a specialized worker, which compiles click counts and creation dates before passing the results up the chain.

Autonomous Infrastructure Audits

The `list_domains` tool lets an infrastructure agent verify that all custom domains remain active and correctly configured. It flags any missing domains to the manager agent for immediate escalation. Profile consistency gets handled by checking `list_bio_links` and `get_bio_link`. A dedicated compliance agent reads the bio page layouts weekly to ensure all promotional links point to active, approved destinations.

Setup guide

Set up AB.GL 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 AB.GL tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent AB.GL 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="AB.GL Analyst",
        goal="Access and analyze AB.GL data via MCP.",
        backstory="Expert analyst with direct AB.GL access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent AB.GL 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 AB.GL. 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 AB.GL 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 AB.GL MCP in CrewAI

Install crewai[tools] via pip. You pass the Vinkius MCP endpoint URL directly into the mcps array when defining your agent.

You handle that via the MCPServerHTTP class. Apply a tool_filter to ensure your analysis agent only accesses get_link_stats while your execution agent handles creation.

The framework maintains shared context across the crew. When one agent generates a short link, the others instantly know the URL and can use it in their respective tasks.

CrewAI natively supports stdio, SSE, and Streamable HTTP. The Vinkius endpoint handles the connection automatically based on your client configuration.

Agents interact with your custom domains, destination URLs, and traffic metrics. Vinkius executes these operations within isolated containers that discard all state the millisecond the request finishes.

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