How to Use the Flagsmith MCP in CrewAI

Q: What is the best way to restrict Flagsmith access in CrewAI?

Use the toolfilter option in your agent configuration. This limits the agents to only the tools they actually need, preventing accidental changes to your production environment.

Build autonomous release crews in CrewAI by letting agents monitor and adjust Flagsmith configurations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Flagsmith MCP to CrewAI

Create your Vinkius account to connect Flagsmith 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 Flagsmith with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous flag monitoring

Assign a monitor agent to periodically run `get_environment_flags` to track the state of your production features. If a flag deviates from the expected state, the agent detects the drift. This keeps your crew informed about the current system status without human oversight. It acts as a continuous audit of your configuration.

Collaborative flag updates

Use `update_flag_v2` when your analyst agent determines a feature needs to be toggled. The crew works together to decide when to push these changes. This removes the bottleneck of manual updates. Your agents handle the logic based on the data they analyze from your environment.

Targeted identity testing

Have your research agent use `identify_user` to simulate behavior for specific segments. This allows the crew to test how different users experience new features. By checking `get_identity_flags`, the agents confirm the rollout is correct before you finalize the deployment. It turns feature testing into an automated team effort.

Setup guide

Set up Flagsmith 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 Flagsmith tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You pass the server URL directly into the agent definition. The agents then have direct access to the toolset for monitoring or updating your flags.

You can set up a crew to poll the environment periodically. The agents compare the output of the tools to their last known state and report any changes.

Use the tool_filter option in your agent configuration. This limits the agents to only the tools they actually need, preventing accidental changes to your production environment.

CrewAI agents use shared memory to store the results of their tool calls. If one agent fetches a flag state, the others can access that information for their own tasks.

The server treats each identity trait as a transient request. Your user ID and trait data are never persisted on our end, ensuring your user information remains private during the agent's analysis.

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