How to Use the Ghost MCP in CrewAI

Q: How do I restrict certain Ghost tools to specific CrewAI agents?

Use the toolfilter parameter when setting up the MCP Server. You can give your analyst agent access to post data while restricting your monitor agent to settings and uptime checks.

Q: How does the Ghost MCP Server secure data accessed by CrewAI?

Your agents pull specific payloads like liststaticpages, and that execution happens inside a secure, ephemeral Vinkius sandbox. Auth tokens are passed per-request and the entire environment is destroyed the second the data returns to your crew.

Deploy multi-agent crews to audit your Ghost CMS. CrewAI agents collaborate to read posts, analyze tags, and map authors.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ghost MCP to CrewAI

Create your Vinkius account to connect Ghost 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 Ghost with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Orchestrate Ghost content audits with CrewAI

The Ghost MCP server acts as a read-only data source for your autonomous agent teams. A researcher agent calls `list_published_posts` to gather recent articles, then hands the data to an analyst agent that reads the content using `get_post_by_slug`. These agents share memory and collaborate without human intervention. You set the goals, and the crew determines the exact sequence of reads required to map your publication's entire output.

Analyze authors and taxonomies

Assign a dedicated agent to monitor your site structure. This agent runs `list_content_tags` and `list_blog_authors` to build a complete picture of your editorial team. It then drills into specific profiles using `get_author_details` and `get_tag_details`. Because CrewAI supports hierarchical execution, a manager agent can evaluate the researcher's findings. If the data looks incomplete, the manager instructs the researcher to pull `list_static_pages` to ensure no content is missed.

Track settings and verify uptime

A monitor agent can continuously check your site's health and configuration. It runs `verify_api_connection` to confirm the CMS is online, then pulls `get_site_settings` and `list_subscription_tiers` to verify your monetization rules. You control exactly which tools each agent sees. Using the `tool_filter` parameter, you can restrict the monitor agent to settings tools while giving the researcher agent exclusive access to the blog content.

Setup guide

Set up Ghost 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 Ghost tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass the server URL directly into the mcps array when defining your agent. For more granular control, import MCPServerHTTP from crewai.mcp and configure the connection manually.

No. This integration provides read-only access. Your crew can read, analyze, and report on existing posts, but they cannot create or modify records in the database.

Use the tool_filter parameter when setting up the MCP Server. You can give your analyst agent access to post data while restricting your monitor agent to settings and uptime checks.

Yes. The framework supports stdio, SSE, and Streamable HTTP transports natively. You just provide the endpoint and the agents handle the underlying communication.

Your agents pull specific payloads like `list_static_pages`, and that execution happens inside a secure, ephemeral Vinkius sandbox. Auth tokens are passed per-request and the entire environment is destroyed the second the data returns to your crew.

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