How to Use the Kevel MCP in CrewAI

Q: How do I add these tools to my CrewAI agents?

Install crewaitools and pass the server URL into the mcps parameter of your Agent definition. For advanced setups, import MCPServerHTTP from crewai.mcp to selectively filter which tools the agent can see.

Q: Can I limit which ad tools my agents use?

Yes. You can use the toolfilter parameter to restrict specific agents. For example, you might let one agent use listcreatives while restricting another to just listzones.

Deploy autonomous CrewAI agent teams to monitor and analyze your Kevel ad inventory.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kevel MCP to CrewAI

Create your Vinkius account to connect Kevel 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 Kevel with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assign Kevel Ad Ops to CrewAI Teams

This MCP Server equips your CrewAI agents with direct read access to the Kevel Management API. You can assign one agent to act as an Inventory Analyst, constantly polling `list_campaigns` and `list_flights` to track active ad delivery. Another agent can take that output and cross-reference it. The first agent finds the IDs, and the second agent runs `get_campaign` or `get_advertiser` to compile a deep-dive report on specific client performance.

Hierarchical Inventory Mapping

Map your entire ad network autonomously. A manager agent can delegate tasks, asking a subordinate to run `list_sites` and `list_zones` to build a complete picture of available placements. The crew shares this context in memory. Once the zones are mapped, a different agent can check `list_channels` and `list_ad_types` to see exactly what formats fit where, entirely without human intervention.

Continuous Creative Auditing via MCP Server

Stop checking ad assets manually. You can spin up a monitor agent that periodically runs `list_ads` and `list_creatives` to verify that the right images are attached to the right campaigns. If something looks wrong, a moderator agent can flag the discrepancy. Pass the server URL directly into your `mcps` array and the crew immediately knows how to query your ad engine.

Setup guide

Set up Kevel 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 Kevel tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Install `crewai[tools]` and pass the server URL into the `mcps` parameter of your Agent definition. For advanced setups, import `MCPServerHTTP` from `crewai.mcp` to selectively filter which tools the agent can see.

No, this integration only supports read operations. Your crew can use `get_campaign` to check if an ad is running, but they cannot change its status.

It removes the ad ops bottleneck. Instead of a human pulling reports, your specialized agents collaborate to analyze `list_flights` and `list_advertisers` data autonomously.

Yes. You can use the `tool_filter` parameter to restrict specific agents. For example, you might let one agent use `list_creatives` while restricting another to just `list_zones`.

Your proprietary advertiser lists and ad assets remain strictly confidential. The MCP Server routes through an ephemeral sandbox where auth is handled securely, meaning your agents only see what the specific endpoint token exposes.

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