How to Use the Cosmic MCP in CrewAI

Q: How do I pass Cosmic tools to a CrewAI agent?

Pass your Vinkius server URL directly into the mcps array when defining your CrewAI agent. For advanced setups, use the MCPServerHTTP class from the MCP package to filter specific tools.

Q: How do I restrict a CrewAI agent from deleting Cosmic documents?

Use the toolfilter option in MCPServerHTTP to restrict MCP tool access. You can expose read-only tools like getsingleobject while completely hiding destructive tools like wipecmsobject.

Run autonomous agent crews to draft, audit, and clean your Cosmic CMS content 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 Cosmic MCP to CrewAI

Create your Vinkius account to connect Cosmic 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 Cosmic with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Operate a collaborative CrewAI team over your MCP Server

Analyzing cloud logs uses `get_single_object` to extract explicit payload IDs and inform your agent crew. One agent can read these logs while another runs `create_cms_object` to draft new JSON payloads based on those insights. The crew works in sequence or hierarchies. They share memory and context, meaning the output of the analysis agent immediately informs the schema structure used by the writer.

Monitor content models for schema drift

Mapping out your content models relies on `get_schema_details` to verify active fields and prevent validation errors. A moderator agent queries this tool along with `list_schema_types` to check rules. If it detects structural changes, it alerts the rest of the crew. This prevents other agents from attempting to write invalid payloads to your headless CMS.

Purge storage buckets automatically

Scanning your media storage uses `list_uploaded_media` to identify orphaned files across your buckets. One agent scans your media files while another verifies active associations using `get_media_asset`. When the crew identifies unused files, it executes `wipe_media_asset` to purge them. This keeps your buckets clean without requiring manual intervention from your development team.

Setup guide

Set up Cosmic 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 Cosmic tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass your Vinkius server URL directly into the `mcps` array when defining your CrewAI agent. For advanced setups, use the `MCPServerHTTP` class from the MCP package to filter specific tools.

Yes, agents share access to the configured tools. One agent can read schema rules via `list_schema_types` while another simultaneously updates drafts using `patch_cms_object`.

This setup supports stdio, SSE, and Streamable HTTP transports. You can configure the communication protocol depending on whether you run your crew locally or in a cloud container.

Use the `tool_filter` option in `MCPServerHTTP` to restrict MCP tool access. You can expose read-only tools like `get_single_object` while completely hiding destructive tools like `wipe_cms_object`.

Your CMS payloads, media files, and document rows are processed entirely in memory during the crew's execution. Vinkius handles the underlying MCP Server in an ephemeral sandbox with a strict zero-retention policy.

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