How to Use the Forgejo (Gitea Fork) MCP in CrewAI

Q: How do I configure the Forgejo (Gitea Fork) MCP server in CrewAI?

Pass the server URL directly into your agent's mcps array. CrewAI connects over HTTP or stdio and automatically maps the Forgejo tools to the agent's capabilities.

Q: How do I restrict the token generation MCP tool in CrewAI?

Use the toolfilter parameter in MCPServerHTTP. Expose createtoken only to your designated security agent, while restricting your standard developer agents to version checks and workflow triggers.

Q: Does CrewAI support autonomous version checks for Forgejo (Gitea Fork)?

It does. You can schedule a crew to run daily, calling getforgejoversion across your infrastructure and compiling an autonomous health report without human intervention.

Deploy autonomous agent crews to monitor Forgejo instances, manage tokens, and trigger CI/CD pipelines 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 Forgejo (Gitea Fork) MCP to CrewAI

Create your Vinkius account to connect Forgejo (Gitea Fork) 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 Forgejo (Gitea Fork) with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous CI/CD Execution

Stop manually clicking buttons to deploy code. You assign a Deployment Agent in CrewAI to watch your release schedule. When the time comes, this agent autonomously calls `dispatch_workflow` to kick off your Forgejo Actions. You can pair it with a QA Agent. Once the deployment finishes, the QA Agent inspects the environment and reports back to the crew. The entire release cycle happens without a human touching the keyboard.

Multi-Agent Version Auditing via MCP Server

Managing multiple self-hosted instances gets messy fast. You spin up an Auditor Agent equipped with this MCP Server to map your infrastructure. It hits every endpoint and calls `get_forgejo_version` and `get_gitea_version`. The agent compiles the metadata into a single report, identifying which servers need patching. It shares this memory with a Manager Agent, who then decides whether to schedule maintenance or ignore the drift.

Delegated Token Provisioning

You don't want every agent holding admin credentials. CrewAI lets you restrict tools to specific roles. You give the `create_token` tool exclusively to a Security Agent. When a worker agent needs temporary access to push code, it asks the Security Agent. The Security Agent generates a short-lived token, hands it over, and logs the transaction. You get strict separation of concerns within your autonomous crew.

Setup guide

Set up Forgejo (Gitea Fork) 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 Forgejo (Gitea Fork) tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

    task = Task(
        description="List recent Forgejo (Gitea Fork) 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 Forgejo. 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 Forgejo (Gitea Fork) 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 Forgejo (Gitea Fork) MCP in CrewAI

Pass the server URL directly into your agent's `mcps` array. CrewAI connects over HTTP or stdio and automatically maps the Forgejo tools to the agent's capabilities.

Yes, if you configure them to run in parallel. A crew can have five different agents calling `dispatch_workflow` across five different repositories at the exact same time.

Use the `tool_filter` parameter in `MCPServerHTTP`. Expose `create_token` only to your designated security agent, while restricting your standard developer agents to version checks and workflow triggers.

It does. You can schedule a crew to run daily, calling `get_forgejo_version` across your infrastructure and compiling an autonomous health report without human intervention.

The crew holds the ability to trigger code execution and generate access tokens. Because CrewAI operates autonomously, a misconfigured agent could spawn excessive tokens or spam your CI runners with workflow dispatches. You must strictly scope the base API token used by the server.

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