How to Use the Keywords AI MCP in CrewAI

Q: How do I configure CrewAI to use the Keywords AI tools?

Install crewaitools. Pass your endpoint directly into the mcps array parameter when defining your agent. The framework handles the MCP tool discovery automatically.

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

Yes. Use MCPServerHTTP from crewai.mcp and apply a toolfilter. You can give your finance agent access to getcredits while hiding listrequests.

Q: Do CrewAI agents share data from Keywords AI tools?

They share memory during a task execution. If Agent A runs getusagestats, Agent B can read those metrics from the shared context to write a summary report.

Deploy autonomous multi-agent teams in CrewAI to monitor, analyze, and optimize your LLM gateway traffic.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Keywords AI MCP to CrewAI

Create your Vinkius account to connect Keywords AI 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 Keywords AI with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assign a Dedicated Gateway Monitor

The Keywords AI MCP Server exposes `list_alerts` and `check_keywordsai_status` so you can dedicate a specific CrewAI agent entirely to uptime monitoring. This monitor agent constantly watches the gateway, looking for latency spikes or rate limit warnings. When the monitor finds an issue, it passes the context to a moderator agent. The moderator then adjusts your application's routing logic to avoid the degraded provider. It is entirely autonomous system administration.

Generate Automated Usage Reports

`get_analytics`, `get_usage_stats`, and `list_requests_by_model` give your research agent the raw data needed to audit your entire engineering team's LLM spend. The agent pulls the metrics, categorizes the costs, and identifies which models waste the most tokens over the MCP protocol. Another agent takes that analysis and formats it into a weekly markdown report for DevOps. You get a complete breakdown of where your API budget went without writing a single SQL query or opening a dashboard.

Audit Team Activity with CrewAI

`list_users` and `get_user` allow your security agent to track exactly who has access to your gateway. It cross-references active team members against your internal directory to find orphaned accounts. If a user shows unusual activity, the agent uses `list_requests` to pull their recent API calls. The crew analyzes the payloads for prompt injection or unauthorized model usage, acting as an automated security guard for your LLM infrastructure.

Setup guide

Set up Keywords AI 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 Keywords AI tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Install `crewai[tools]`. Pass your endpoint directly into the `mcps` array parameter when defining your agent. The framework handles the MCP tool discovery automatically.

Yes. Use `MCPServerHTTP` from `crewai.mcp` and apply a `tool_filter`. You can give your finance agent access to `get_credits` while hiding `list_requests`.

They share memory during a task execution. If Agent A runs `get_usage_stats`, Agent B can read those metrics from the shared context to write a summary report.

The framework itself runs tasks sequentially or hierarchically when triggered. You trigger the crew via your own cron job or CI/CD pipeline to run daily audits.

This server handles raw API payloads, model routing data, and cost metrics. Vinkius hosts the connection in a strict ephemeral sandbox. No database stores your logs, and the server instance is destroyed entirely after your crew finishes its task.

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