How to Use the Crystal Matcher MCP in AutoGen

Q: Can I use Crystal Matcher for complex multi-step decision making with AutoGen?

Yes. One agent can use querycrystalsbyintent, and then another agent takes that result to run the chakra finder. The negotiation between them converges on a much stronger recommendation.

Force consensus on crystal pairings using AutoGen's multi-agent debate framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Crystal Matcher MCP to AutoGen

Create your Vinkius account to connect Crystal Matcher to AutoGen 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 Crystal Matcher with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Facilitate debates across multiple expert agents.

You don't just ask a question. You set up competing agents—one might run `query_crystals_by_intent` based on emotional needs, while another runs `find_crystals_by_chakra` for energetic alignment. They debate the best answer.

Challenge assumptions with structured data.

A third agent can use `filter_crystals_by_element` to challenge the initial list, forcing the group to consider elemental compatibility. This is how you get a decision that's actually vetted by multiple perspectives.

Get consensus on crystal specifics.

After the agents debate which crystals are best, one can run `get_crystal_details` to confirm key facts—like specific usage instructions or rarity. This final verification step prevents any single agent from making a mistake.

Setup guide

Set up Crystal Matcher MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Crystal Matcher tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Crystal Matcher_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Crystal Matcher data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Crystal Matcher_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Crystal Matcher data")
    print(result.messages[-1].content)

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 Crystal Matcher. 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 Crystal Matcher 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 Crystal Matcher MCP in AutoGen

You set up multiple agents to talk to the MCP server. They might debate whether crystals should be filtered by element or chakra first, using tools like `filter_crystals_by_element` and `find_crystals_by_chakra` in a back-and-forth discussion.

Yes. One agent can use `query_crystals_by_intent`, and then another agent takes that result to run the chakra finder. The negotiation between them converges on a much stronger recommendation.

This MCP touches crystal catalog data, including element names and chakra alignments. Multiple agents can argue over which combination of these traits is most effective for the user's goal.

It provides objective facts that the debating agents must consider. If one agent suggests a crystal, another can run `get_crystal_details` to validate its claims before consensus is reached.

Definitely. The debate structure forces multiple perspectives on the data (like intent or chakra), so you don't rely on just one tool call or single interpretation.

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