How to Use the Dev.to (Forem) MCP in CrewAI

Q: How can I prevent a rogue CrewAI agent from deleting all my Dev.to (Forem) posts?

Use toolfilter when you set up the MCP server connection in CrewAI. You can create a 'Publisher' agent that can createarticle and updatearticle, but explicitly deny it access to the unpublisharticle tool. That tool could be reserved for a separate, highly-controlled 'Admin' agent.

Q: Can I get my authenticated user details within a CrewAI agent?

Yes, the getme tool is available. You can create an agent that calls it to fetch the profile details of the user whose API key is being used for authentication. This is useful for personalizing actions or reports.

Deploy a crew of specialized AI agents to autonomously manage your Dev.to content strategy with CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dev.to (Forem) MCP to CrewAI

Create your Vinkius account to connect Dev.to (Forem) 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 Dev.to (Forem) with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble a Content Strategy Crew

CrewAI lets you assign roles. Create a 'Researcher' agent that uses `list_articles` and `list_videos` to analyze trending topics on Dev.to. Its findings are passed to a 'Writer' agent, whose only job is to take those topics and use `create_article` to generate drafts. This division of labor is what makes CrewAI powerful. A third 'Editor' agent can then review the drafts, perhaps using `get_article_by_id` to fetch the content and suggest edits, before a 'Publisher' agent finally uses `update_article` to push it live. It's a full content assembly line.

Your Autonomous Dev.to MCP Server Team

Go beyond simple posting. Set up a 'Moderator' agent that periodically runs `list_my_articles` to check post stats. If a post has low engagement after a week, it could use `unpublish_article` to pull it back into drafts for revision. This is proactive content management, running 24/7. You can also have a 'Welcome' agent for your organization. It can use `list_org_users` to spot new members, then use other tools (like a messaging MCP server) to send them a welcome note. This Dev.to MCP server becomes one part of a larger, automated operation.

Fine-Grained Tool Access for Agents

Not every agent in your crew should have full access. Using CrewAI's `tool_filter` with the MCP server, you can restrict which agent can use which tool. Your 'Researcher' agent might only get read-only tools like `list_articles` and `get_user`. This is a critical security practice. Only the 'Publisher' agent gets access to `create_article` and `update_article`. The 'Moderator' might be the only one with permission for `unpublish_article`. This limits the blast radius if an agent misunderstands its task.

Setup guide

Set up Dev.to (Forem) 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 Dev.to (Forem) tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

    task = Task(
        description="List recent Dev.to (Forem) 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 Dev.to (Forem). 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 Dev.to (Forem) 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 Dev.to (Forem) MCP in CrewAI

It's straightforward. You can pass your Vinkius MCP server URL directly into the `mcps` list when defining an agent. For more control, use `MCPServerHTTP` from `crewai.mcp` to filter which specific tools from the server an agent can access.

Yes, this is exactly what CrewAI is for. You'd create a 'Researcher' agent using `list_articles` to find ideas. Then, you'd create a 'Writer' agent that takes those ideas as input and uses the `create_article` tool.

Use `tool_filter` when you set up the MCP server connection in CrewAI. You can create a 'Publisher' agent that can `create_article` and `update_article`, but explicitly deny it access to the `unpublish_article` tool. That tool could be reserved for a separate, highly-controlled 'Admin' agent.

Yes, the `get_me` tool is available. You can create an agent that calls it to fetch the profile details of the user whose API key is being used for authentication. This is useful for personalizing actions or reports.

CrewAI agents run on your infrastructure, and they communicate with the ephemeral Vinkius MCP server. You can use CrewAI's `tool_filter` to ensure only specific agents can even attempt to access sensitive tools like `get_me` or `list_my_articles`. This provides granular, role-based control over what data each autonomous agent can touch.

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