How to Use the Formilla MCP in CrewAI

Q: How do I add Formilla tools to a CrewAI agent?

Pass the server URL directly into the mcps array when defining your agent. The framework will automatically discover and load the available tools.

Q: Can I restrict which Formilla tools a specific CrewAI agent uses?

Yes. Import MCPServerHTTP and use the toolfilter argument. This lets you give one agent access to getconversation while blocking it from deletecontact.

Deploy a team of autonomous agents to monitor website visitors and manage chat logs in CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Formilla MCP to CrewAI

Create your Vinkius account to connect Formilla 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 Formilla with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

CrewAI agent collaboration

One agent cannot handle an entire support queue effectively. You can assign a monitoring agent to run `list_conversations` continuously, looking for incoming messages that need immediate attention. Once it finds an active thread, it hands the ID off to a researcher agent. That second agent runs `get_conversation` to read the chat history and `get_contact` to pull the customer profile, building a complete brief for your human team.

Autonomous contact syncing

Keep your database clean without manual data entry. You can build a specialized data-entry crew that uses `list_contacts` to audit your existing records for missing fields or outdated information. When the crew finds a discrepancy, it takes action. It can call `update_contact` to fix typos, or run `delete_contact` to purge spam accounts. The agents handle the cleanup sequentially based on the rules you define.

Formilla MCP Server traffic analysis

Turn raw traffic into actionable sales leads. Assign an analyst agent to execute `list_visitors` and gather data on everyone currently browsing your site. The agent can cross-reference those visitors against your existing database using `search_contacts`. If a high-value client is on the pricing page, the crew can trigger an escalation protocol to notify a sales rep immediately.

Setup guide

Set up Formilla 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 Formilla tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass the server URL directly into the `mcps` array when defining your agent. The framework will automatically discover and load the available tools.

Yes. Import `MCPServerHTTP` and use the `tool_filter` argument. This lets you give one agent access to `get_conversation` while blocking it from `delete_contact`.

It does. You can set up a manager agent that reviews the output of a subordinate agent before allowing it to run `upsert_contact` to modify a customer record.

You can use stdio, Server-Sent Events (SSE), or Streamable HTTP. The framework handles the connection details based on your configuration.

No. The names, emails, and conversation logs retrieved by your agents remain strictly inside your local runtime. The MCP architecture prevents any unauthorized external access to your payloads.

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