How to Use the Modash MCP in CrewAI

Q: How do I assign Modash tools to specific agents in CrewAI?

You pass the Vinkius MCP Server URL directly into the mcps parameter of your specialized Agent. For instance, you can give the researcher agent access to searchyoutube while keeping report tools restricted to the analyst.

Q: Do I need to install local dependencies to use Modash with CrewAI?

No, you only need to install crewai and pass the HTTP transport URL. The MCP Server runs entirely in Vinkius's managed cloud infrastructure, eliminating local setup friction.

Q: How does the crew handle missing profile data?

If getrawprofile returns incomplete fields, your analyst agent uses its internal reasoning to decide whether to skip the creator or attempt to find them on another platform using searchinstagram.

Deploy autonomous agent crews to discover and vet creators using CrewAI and the Modash MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Modash MCP to CrewAI

Create your Vinkius account to connect Modash 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 Modash with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Influencer Vetting via CrewAI

`search_instagram` lets your discovery agent hunt for prospective creators while an analyst agent uses `get_instagram_report` to verify their audience. The two agents share memory to avoid duplicating search queries. CrewAI coordinates this division of labor autonomously. You define the roles, and the crew determines which tools to execute to verify that a creator's audience matches your target brand.

Cross-Platform Channel Auditing

`get_youtube_report` provides the raw metrics your auditing agent needs to calculate true conversion potential. A separate moderator agent can flag channels that show signs of inactive subscribers. This setup isolates the data retrieval from the decision-making process. Your crew runs through thousands of channels sequentially, compiling a clean list of verified prospects without human intervention.

Niche Targeting and Categorization

`list_interests` allows your research agent to map out the exact target demographics before initiating any searches. The agent uses these IDs to narrow down potential creators on TikTok and YouTube. By feeding these precise taxonomies into `search_tiktok`, your crew avoids wasting API calls on irrelevant categories. The agents self-correct their search terms based on the results they receive from the MCP Server.

Setup guide

Set up Modash 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 Modash tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You pass the Vinkius MCP Server URL directly into the `mcps` parameter of your specialized Agent. For instance, you can give the researcher agent access to `search_youtube` while keeping report tools restricted to the analyst.

Yes, CrewAI can run hierarchical or sequential tasks where multiple agents query `get_tiktok_report` simultaneously. Vinkius handles the concurrent connections securely in the cloud.

No, you only need to install `crewai` and pass the HTTP transport URL. The MCP Server runs entirely in Vinkius's managed cloud infrastructure, eliminating local setup friction.

If `get_raw_profile` returns incomplete fields, your analyst agent uses its internal reasoning to decide whether to skip the creator or attempt to find them on another platform using `search_instagram`.

Yes, all creator profile details and audience demographics retrieved through `get_instagram_report` are encrypted in transit. Vinkius executes each tool call in an ephemeral, zero-trust container that leaves no footprint.

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