How to Use the Indy MCP in CrewAI

Q: How do I share the Indy MCP Server across multiple CrewAI agents?

You pass the Vinkius server URL in the mcps list when defining your CrewAI agents. This gives both your Intake Agent and Triage Agent access to tools like createform and listrecords.

Q: Can a CrewAI agent autonomously delete forms using Indy?

Yes, if you grant access to the deleteform tool. You can use CrewAI's tool filtering to limit this capability to a specific manager agent, preventing lower-level agents from accidentally removing active questionnaires.

Q: How do CrewAI agents collaborate using Indy record data?

One agent can run listrecords to gather raw submissions, pass the resulting data to a writer agent to draft a proposal, and have a third agent check team availability via getuser.

Q: How does the Indy and CrewAI integration protect my agency's client data?

Your database records fetched via getrecord and user lists from listusers are processed locally within your CrewAI environment or secure Vinkius sandboxes. No external parties can access your client profiles or platform account info.

Deploy specialized agent crews to manage forms, track submissions, and handle client communication autonomously with Indy and CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Indy MCP to CrewAI

Create your Vinkius account to connect Indy 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 Indy with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy a Multi-Agent Onboarding Crew with Indy MCP Server

The `create_form` and `get_form` tools enable your specialized agents to design and audit client touchpoints. In a CrewAI setup, you can assign an Intake Agent to build onboarding forms while a Quality Agent uses `get_form` to inspect the questions for clarity. You don't have to manually check every layout. This collaborative setup ensures your freelance business presents polished forms to prospects. Because this Indy MCP Server integrates directly with CrewAI's shared memory, agents remember previous form layouts and continuously refine their designs.

Autonomous Submission Analysis and Routing

The `list_records` and `get_record` tools provide your agent team with a direct feed of incoming client submissions. A Researcher Agent can pull new submissions, while an Analyst Agent processes the specific details of each lead. The crew then collaborates to match the prospect's needs with your team's availability using `list_users`. This entire triage process happens autonomously, freeing you from manual lead sorting.

Manage Live Webhook Feeds for Team Alerts

The `create_webhook` and `list_webhooks` tools let your crew establish direct alert channels for new business events. A Coordinator Agent can monitor your active webhooks and set up new listeners whenever a new client campaign kicks off. If an endpoint goes offline, a Monitor Agent detects the failure and uses `delete_webhook` to clean up the broken route before spawning a replacement. This keeps your communication channels clear and active.

Setup guide

Set up Indy 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 Indy tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You pass the Vinkius server URL in the `mcps` list when defining your CrewAI agents. This gives both your Intake Agent and Triage Agent access to tools like `create_form` and `list_records`.

Yes, if you grant access to the `delete_form` tool. You can use CrewAI's tool filtering to limit this capability to a specific manager agent, preventing lower-level agents from accidentally removing active questionnaires.

One agent can run `list_records` to gather raw submissions, pass the resulting data to a writer agent to draft a proposal, and have a third agent check team availability via `get_user`.

CrewAI supports stdio, SSE, and Streamable HTTP. For most managed environments, connecting via the HTTP MCP transport hosted on Vinkius is the easiest way to expose tools like `get_account_info` to your crew.

Your database records fetched via `get_record` and user lists from `list_users` are processed locally within your CrewAI environment or secure Vinkius sandboxes. No external parties can access your client profiles or platform account info.

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