How to Use the Hexometer MCP in CrewAI

Q: How do multiple CrewAI agents share Hexometer data?

They use shared memory. If Agent A runs checkbrokenlinks, Agent B can read the resulting 404 list from memory and attempt to find the referring pages in your CMS.

Deploy autonomous QA crews that monitor, audit, and report on site health using CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hexometer MCP to CrewAI

Create your Vinkius account to connect Hexometer 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 Hexometer with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assign SEO Audits to Specialized Agents

A dedicated research agent in CrewAI can pull your entire property list using `list_monitored_sites` and hand the URLs off to an analyst agent. That second agent then executes `run_seo_audit` on every single domain to build a massive, cross-referenced compliance report. This hierarchical MCP execution means one agent handles discovery while another handles the deep analysis. You stop writing custom scripts to loop through properties because the crew negotiates the workload autonomously.

Run an Autonomous SRE Crew

Connecting the MCP Server lets you stand up a monitor agent that constantly evaluates `list_recent_alerts` for incoming anomalies. If an alert triggers, it passes context to a diagnostic agent that pulls `get_uptime_stats` and `get_site_health` to determine if the issue is an isolated spike or a systemic failure. The crew shares memory, so the diagnostic agent already knows which endpoint failed and when. It compiles a root cause analysis and pages your real engineers with actual context, not just a generic downtime ping.

Restrict the Hexometer MCP Server via CrewAI

You can use tool_filter in MCPServerHTTP to give a frontend QA agent access to exactly two tools: `check_speed_mobile` and `check_page_errors`. The agent tests the mobile viewport, finds heavy JavaScript assets, and writes a Jira ticket for the performance regression. By locking down the toolset, you prevent the QA agent from hallucinating and trying to check `get_security_status`. It stays entirely focused on frontend performance metrics and asset sizes.

Setup guide

Set up Hexometer 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 Hexometer tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass the Vinkius endpoint directly into the mcps array on your agent definition. For tighter control, import MCPServerHTTP from crewai.mcp and define explicit tool filters.

Yes. You can set up a sequential crew that runs on a cron job, waking up to check `list_recent_alerts` and escalating issues to a human moderator only when severe.

They use shared memory. If Agent A runs `check_broken_links`, Agent B can read the resulting 404 list from memory and attempt to find the referring pages in your CMS.

The agent reads the error response, adjusts its parameters, and tries again. If `run_seo_audit` fails due to a malformed URL, the agent corrects the string and re-executes.

The MCP integration guarantees strict data boundaries. The only information passed over the wire is the explicit URL targeted by `check_speed_desktop` or similar tools. Vinkius drops the connection immediately after execution, ensuring your internal QA discussions never leak into the remote sandbox.

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