How to Use the Ada MCP in CrewAI

Q: How do I connect my CrewAI agents to the Ada MCP Server?

Pass your Vinkius endpoint URL directly into the agent's mcps list. This gives your specialized support crew instant access to your help articles and user profiles.

Q: Can I restrict which Ada tools my CrewAI agents can use?

Yes, use the MCPServerHTTP class from the CrewAI library. Apply a toolfilter to ensure your research agent can only run listconversations and not modify articles.

Deploy specialized agent teams to audit Ada conversations and update help articles using CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ada MCP to CrewAI

Create your Vinkius account to connect Ada 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 Ada with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run autonomous support audits with CrewAI

Set up a research agent to scan your support history using `list_conversations`. A second analysis agent can then identify unresolved issues that keep popping up. This MCP Server allows your crew to collaborate without human intervention. The agents share context in memory, making it easy to spot trends across hundreds of customer chat logs.

Automated knowledge base drafting via CrewAI

When your audit agent finds a gap in your documentation, it passes the task to a writer agent. That agent uses `create_article` to draft a new help file immediately. Before publishing, a manager agent can call `list_articles` to make sure you aren't creating a duplicate. The entire operation runs autonomously, keeping your support center fresh.

Multi-agent customer profiling

Your support crew needs deep context to solve complex tickets. One agent can pull user records via `get_end_user` while another analyzes past chat logs to map out the customer's journey. Because CrewAI supports hierarchical execution, a supervisor agent coordinates these tools. Your agents get a complete picture of the customer's history before recommending a resolution.

Setup guide

Set up Ada 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 Ada tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass your Vinkius endpoint URL directly into the agent's `mcps` list. This gives your specialized support crew instant access to your help articles and user profiles.

Yes, use the `MCPServerHTTP` class from the CrewAI library. Apply a `tool_filter` to ensure your research agent can only run `list_conversations` and not modify articles.

The crew uses shared memory to pass user profiles fetched by `get_end_user` between agents. This keeps your agents aligned without making redundant API calls to the server.

No, Vinkius hosts the MCP Server for you. Your CrewAI Python script connects to the managed endpoint, handling all transport details behind the scenes.

Yes, it is. Vinkius runs the connection inside an isolated V8 sandbox. Your draft articles and customer records are never stored, keeping your internal knowledge base completely private.

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