How to Use the Toky MCP in CrewAI

Q: How does CrewAI research using Toky contact data?

The crew uses listcontacts to pull a full history of contacts. This shared memory allows different agents—like the researcher and the analyzer—to all reference the same pool of information.

Q: Does CrewAI support multi-step actions with Toky calls?

Yes. An agent can first use getcall to research a call, then pass that data to another agent which summarizes it. This sequence is what makes the crew autonomous.

Q: Can I configure selective tool exposure for the MCP Server in CrewAI?

Absolutely. When setting up your agent mcps, you can use a toolfilter to ensure that only the specific tools needed for one operational workflow are exposed.

Run autonomous Toky communication operations using CrewAI's specialized agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Toky MCP to CrewAI

Create your Vinkius account to connect Toky 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 Toky with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

List Toky Contacts

The `list_contacts` tool allows your research agent to gather a paginated list of all relevant contacts in Toky. This provides the foundational data set for any operation. The whole crew can then share this memory.

Get Call Details

A specialized analysis agent uses `get_call` to pull detailed records for a specific call. It reads the metadata and passes it off to another agent for sentiment scoring or summary generation. This is how the crew collaborates.

Send SMS Message

When your operation concludes, an action agent uses `send_sms` to dispatch a message via Toky. The autonomous pipeline handles the messaging step without human input, completing the task end-to-end.

Setup guide

Set up Toky 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 Toky tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

The crew uses `list_contacts` to pull a full history of contacts. This shared memory allows different agents—like the researcher and the analyzer—to all reference the same pool of information.

Yes. An agent can first use `get_call` to research a call, then pass that data to another agent which summarizes it. This sequence is what makes the crew autonomous.

The system supports listing contacts and calls, getting details on specific records, and finally taking action by sending an SMS message using `send_sms`.

Absolutely. When setting up your agent mcps, you can use a `tool_filter` to ensure that only the specific tools needed for one operational workflow are exposed.

The core data types are Contact records, Call metadata, and SMS status. This combination allows your autonomous agents to research, analyze, and act upon communication information.

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