How to Use the Ashby MCP in AutoGen

Q: How do I initialize the Ashby MCP Server in AutoGen?

Install autogen-extmcp. Use mcpservertools with a StreamableHttpServerParams object pointing to your Vinkius endpoint, then pass the list to your AssistantAgent.

Q: Can multiple agents share the same MCP connection?

Yes. The McpToolAdapter handles schema conversion for all agents in the chat. You decide which specific agents get permission to execute writes.

Build AutoGen debating squads that evaluate Ashby candidates autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ashby MCP to AutoGen

Create your Vinkius account to connect Ashby 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 Ashby with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy agents to review Ashby profiles

Your technical agent and culture-fit agent pull records via `get_ashby_candidate`. They read the same resume but evaluate it from competing perspectives. The MCP protocol feeds them the identical JSON. The technical agent demands specific coding skills while the culture agent looks for communication flags. Consensus emerges after a few rounds of internal chat. The system automatically triggers `get_ashby_application` to check if this person applied before. It then outputs a unified recommendation to your hiring manager.

Automate interview slot selection

Resolving calendar conflicts requires pulling data through `list_ashby_interviews`. A scheduling agent reads the open blocks. A separate load-balancing agent checks `list_ashby_users` to ensure no single engineer conducts too many technical screens. They negotiate the optimal panel configuration. Once they agree on a lineup, the AutoGen framework passes the final parameters back to the user for approval. You skip the manual calendar tetris.

Audit the Ashby MCP Server pipeline

Routine checks on your hiring velocity start with `list_ashby_jobs`. An analytical agent compares open headcount against the active pipeline generated by `list_ashby_applications`. If the funnel looks weak, it alerts a sourcing agent. That second agent formulates a plan to find more people. The entire deliberation happens in the background, logging the transcript for your review.

Setup guide

Set up Ashby 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 Ashby 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="Ashby_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Ashby 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="Ashby_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Ashby 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 Ashby. 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 Ashby 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 Ashby MCP in AutoGen

Install `autogen-ext[mcp]`. Use `mcp_server_tools` with a `StreamableHttpServerParams` object pointing to your Vinkius endpoint, then pass the list to your `AssistantAgent`.

Yes. The `McpToolAdapter` handles schema conversion for all agents in the chat. You decide which specific agents get permission to execute writes.

If a lookup returns a 404, the executing agent reports the failure to the group. The supervising agent then suggests an alternative search strategy.

The connection natively supports Streamable HTTP transports. Your agents receive large candidate lists in chunks rather than waiting for the entire payload.

The system transmits private interviewer notes and scoring rubrics. Vinkius secures this by requiring a single endpoint token and executing all tool calls within a locked-down, memory-isolated sandbox.

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