How to Use the GitHub MCP in CrewAI

Q: Can a CrewAI agent search GitHub code for me?

They can. Add searchgithubcode to the agent tools, and it will run the search as part of its task list.

Deploy specialized GitHub agent crews to automate repository monitoring and pull request reviews.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect GitHub MCP to CrewAI

Create your Vinkius account to connect GitHub to CrewAI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup GitHub with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Collaborative GitHub repository research

Assign research tasks to specific agents. One agent uses `list_pull_requests` to find open items, while another uses `get_file_contents` to review the code. This division of labor makes your crew faster. They share memory to ensure the second agent knows exactly what the first one found.

Autonomous issue tracking and resolution

Let your crew handle the backlog. A monitor agent watches for new tickets via `list_repo_issues`, and the fixer agent uses `create_new_issue` to track the response. No human needs to intervene for routine maintenance. The agents work sequentially to keep your project moving forward.

Selective GitHub tool exposure

Control exactly what your agents can do. Use a tool filter to limit the MCP Server to read-only operations like `get_repository_details` for your junior agents. This keeps your repository secure. You give power only where it is needed, preventing accidental writes or unauthorized modifications.

Setup guide

Set up GitHub 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 GitHub tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

    task = Task(
        description="List recent GitHub 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 GitHub. 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.