How to Use the DeveloperHub MCP in CrewAI

Q: How can a CrewAI team monitor a DeveloperHub project for outdated pages?

Assign a 'Monitor' agent the listrecentlyupdatedpages tool. It can run periodically and if a project's pages haven't been updated in a while, it can delegate a task to an 'Analyst' agent to investigate further using other tools from this MCP server.

Q: Can I have one CrewAI agent find DeveloperHub changes and another one summarize them?

Yes, that's a perfect use case. The first agent uses listproductchangelogs to find new entries. It then passes the entry details to a second agent, which uses getdocumentationpagecontent on related pages to write a summary for your team.

Q: How do I give my CrewAI agents access to only some DeveloperHub tools?

When configuring your MCPServerHTTP object in CrewAI, use the toolfilter parameter. This lets you pass a function that decides which tools, like searchdocumentationportal or getaccountmetadata, are exposed to a specific agent or crew.

Deploy an autonomous crew with CrewAI to manage your DeveloperHub portal. Let agents research, write, and verify documentation for you.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DeveloperHub MCP to CrewAI

Create your Vinkius account to connect DeveloperHub 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 DeveloperHub with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble a Documentation Team

Assign roles to a crew of agents to manage your docs autonomously. A 'Watcher' agent can use `list_recently_updated_pages` to monitor for file changes. When it finds one, it tasks a 'Content' agent to fetch the new text with `get_documentation_page_content`. Meanwhile, a 'Changelog' agent can use `list_product_changelogs` to monitor for API updates and ensure the content agent's work aligns with new releases. This divides the labor, letting each agent focus on one part of the problem.

Run Autonomous Project Audits

You can deploy a crew to continuously audit your entire DeveloperHub presence. An 'Auditor' agent starts by calling `list_documentation_projects`. For each project, it assigns a 'Mapper' agent to generate a full site structure using `get_documentation_sitemap`. This crew can identify stale projects, find pages that haven't been updated in months via `list_recently_updated_pages`, or even use `search_documentation_portal` to find and flag forbidden terms. The agents work together, passing tasks and context to each other until the audit is complete.

Your CrewAI Agents' Own MCP Server

This isn't just a set of tools; it's a dedicated workspace for your agents. The 'Researcher' agent can use `search_documentation_portal` to gather context. The 'Analyst' agent can then take that data, fetch full pages with `get_documentation_page_content`, and synthesize a report. The shared memory in CrewAI means the Analyst knows exactly what the Researcher found. This MCP server gives them the specific functions they need to interact with the real world—in this case, your documentation portal.

Setup guide

Set up DeveloperHub 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 DeveloperHub tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Assign a 'Monitor' agent the `list_recently_updated_pages` tool. It can run periodically and if a project's pages haven't been updated in a while, it can delegate a task to an 'Analyst' agent to investigate further using other tools from this MCP server.

Yes, that's a perfect use case. The first agent uses `list_product_changelogs` to find new entries. It then passes the entry details to a second agent, which uses `get_documentation_page_content` on related pages to write a summary for your team.

When configuring your `MCPServerHTTP` object in CrewAI, use the `tool_filter` parameter. This lets you pass a function that decides which tools, like `search_documentation_portal` or `get_account_metadata`, are exposed to a specific agent or crew.

Yes. The tools are stateless and can be used in any execution model. Whether your agents work one after another or in a manager-subordinate structure, they can call these DeveloperHub tools as needed to complete their assigned tasks.

Your agents will be handling your documentation text, project sitemaps, and account metadata from DeveloperHub. Each tool call is a discrete, stateless request sent over a TLS-encrypted connection. Vinkius runs these operations in single-use V8 Isolate sandboxes that are destroyed after execution.

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