How to Use the Denim MCP in CrewAI

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

Install the required tools with pip install crewai "crewaitools". Then pass your Vinkius endpoint URL directly into the mcps array when defining your agent. It connects instantly via SSE or Streamable HTTP.

Q: Can I restrict which Denim tools specific CrewAI agents can access?

Yes, you can lock down permissions per role. Use MCPServerHTTP from crewai.mcp and apply a toolfilter. This lets you give your researcher agent read-only access while reserving contact creation for your action agent.

Let your CrewAI agents build, run, and track Denim marketing campaigns entirely on their own.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Denim MCP to CrewAI

Create your Vinkius account to connect Denim 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 Denim with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Denim Campaign Control

You don't need to manually pull marketing metrics anymore. Assign one CrewAI agent to pull raw performance numbers via MCP using `get_campaign_analytics`, while a second agent cross-references those stats against `get_campaign_details`. They pass this context back and forth in shared memory until they figure out exactly why your open rates dropped. The real trick is letting your agents handle the heavy lifting across your entire account. A manager agent can run `list_marketing_campaigns` to find active pushes, then delegate a researcher to `search_active_campaigns` for specific keywords. They do the digging so you just read the final report.

CrewAI MCP Server for Lead Gen

Stop moving CSV files around. Tell your prospector agent to grab the latest leads via `list_crm_contacts` and group them by behavior. If that agent finds a gap in your targeting, it can instantly call `list_audience_segments` to see what buckets already exist before creating a mess. When your outreach crew lands a new lead, they don't need you to update the database. An action-oriented agent just hits `add_new_contact` and moves on. You build a pipeline where one agent qualifies the lead and another writes the record straight to Denim.

Track Templates and Automations

Marketing workflows break when templates get out of sync. Set up a monitor agent that periodically checks `list_email_templates` to ensure your messaging matches current guidelines. If something looks off, that agent flags it for review before the next blast goes out. You can also keep an eye on the bigger picture without logging into the dashboard. Have a reporting agent call `list_active_automations` every morning. It checks your running sequences and pulls `get_account_metadata` to make sure you aren't hitting API limits.

Setup guide

Set up Denim 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 Denim tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Install the required tools with `pip install crewai "crewai[tools]"`. Then pass your Vinkius endpoint URL directly into the `mcps` array when defining your agent. It connects instantly via SSE or Streamable HTTP.

Yes, you can lock down permissions per role. Use `MCPServerHTTP` from `crewai.mcp` and apply a `tool_filter`. This lets you give your researcher agent read-only access while reserving contact creation for your action agent.

It works perfectly with both sequential and hierarchical setups. A manager agent can review campaign data, then delegate specific update tasks to worker agents based on the tools you exposed to them.

Your agent will receive an error response from the server. Because CrewAI agents have shared memory, they can read the error, call the metadata tool to check current limits, and decide whether to retry or wait.

Vinkius runs this MCP Server inside a V8 Isolate Sandbox that destroys itself after the session ends. Your CRM leads, campaign metrics, and audience segments pass straight through the ephemeral environment. We hold zero persistent data.

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