How to Use the Medium MCP in CrewAI

Q: How do I add the Medium MCP Server to my CrewAI agents?

Pass the server URL directly into the mcps array when defining your agents in Python. The framework automatically discovers and exposes tools from the MCP integration like createdraft to your writing crew.

Q: Can CrewAI agents write to a specific Medium publication?

Yes, the agents can use listpublications to find the correct publication ID. Once identified, they call createpublicationpost to submit the article directly to that publication.

Q: How do CrewAI agents coordinate when editing a Medium draft?

The writer agent first creates the post using createdraft and returns the draft URL. Reviewing the text and finalizing the submission is then handled by the editor agent using its tools.

Q: Does CrewAI support sequential publishing workflows on Medium?

Yes, CrewAI's sequential process model ensures that getmyuserid runs first to verify the account, followed by drafting, and ending with createpublicpost. This step-by-step pipeline guarantees that no posts are published without proper verification.

Deploy a team of specialized CrewAI agents to research, draft, and publish articles to Medium.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Medium MCP to CrewAI

Create your Vinkius account to connect Medium 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 Medium with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate writing teams using this MCP Server

This MCP Server uses `create_draft` to let your CrewAI writer agents collaborate on complex publishing tasks. The research agent gathers technical data, the writer agent drafts the post, and the editor agent refines the markdown directly inside the Medium draft. Using CrewAI's shared memory, the crew coordinates these steps by passing the draft ID to the editor agent. Once approved, the editor agent calls `create_public_post` to publish the final version to your readers.

Manage publications with CrewAI agent teams

The `list_my_publications` tool gives your CrewAI research agent the exact list of targets available for posting on Medium. Deciding which publication fits the article's niche best is handled by the manager agent before triggering the upload. Permissions are checked dynamically by calling `list_contributors` to verify the CrewAI writer agent's status. If the agent is not a contributor, the supervisor agent redirects the post to a draft queue using `create_draft` for manual intervention.

Verify author profiles within CrewAI

The `get_my_user_id` tool allows the CrewAI moderator agent to verify the account identity before starting any publishing run. This ensures that your automated crew never posts content to the wrong user account by mistake. Logging performance metrics inside the CrewAI memory is done by fetching author stats using `get_my_profile`. Analyzing which author profile is best suited for specific content topics becomes automatic for your optimization agents.

Setup guide

Set up Medium 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 Medium tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass the server URL directly into the `mcps` array when defining your agents in Python. The framework automatically discovers and exposes tools from the MCP integration like `create_draft` to your writing crew.

Yes, the agents can use `list_publications` to find the correct publication ID. Once identified, they call `create_publication_post` to submit the article directly to that publication.

The writer agent first creates the post using `create_draft` and returns the draft URL. Reviewing the text and finalizing the submission is then handled by the editor agent using its tools.

Yes, CrewAI's sequential process model ensures that `get_my_user_id` runs first to verify the account, followed by drafting, and ending with `create_public_post`. This step-by-step pipeline guarantees that no posts are published without proper verification.

Your integration token is stored as a secure environment variable on the host running your Python script. The Vinkius MCP host handles all draft bodies and publication data within isolated, zero-trust sandboxes that do not persist any data.

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