How to Use the Ashby MCP in AutoGen

Q: How do I give AutoGen agents access to Ashby?

Use the autogen-extmcp package to load the tools via mcpservertools. Pass that list directly into your AssistantAgent constructor so it can query the ATS.

Q: Do I need to format Ashby API responses for AutoGen?

No, the MCP standard handles that. When an agent calls getjobinfo, the JSON response is automatically converted into a conversational format the other agents can read.

Q: How do I check my connection status?

Tell your primary agent to run getaccountcheck. It will confirm the credentials are valid before the rest of the group chat starts trying to pull candidate data.

Let AutoGen agents manage your Ashby pipeline. Build multi-agent systems that debate candidate qualifications and interview feedback.

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

Agents debate hiring decisions

Single agents miss critical details when reviewing applicants. AutoGen lets you spin up a recruiter agent and a technical agent to review the same profile. They argue over the requirements until they reach a consensus. One agent calls `search_candidates` to find the profile and `get_candidate_info` to read the background. The technical agent scrutinizes the skills, while the recruiter agent checks the active pipeline via `list_interviews` to see if they are moving fast enough.

Connect the Ashby MCP Server

Getting ATS data into a multi-agent chat usually requires custom middleware. This integration provides a standard interface that drops right into your setup. The group chat gets instant read access to the entire recruiting funnel. The system uses McpToolAdapter to map the API schema to your agents automatically. When a manager agent asks about open headcount, a subordinate agent runs `list_jobs` and parses the status filters before reporting back to the group.

Audit application pipelines

Stalled applications ruin the candidate experience. You can deploy a supervisor agent to monitor the queue and flag bottlenecks. It interrogates the data and pushes human recruiters to take action. The supervisor triggers `list_applications` to find out who has been waiting too long. It passes those IDs to an investigator agent, which runs `get_application_info` to read the exact hold-up and propose a resolution in the chat.

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

Use the autogen-ext[mcp] package to load the tools via mcp_server_tools. Pass that list directly into your AssistantAgent constructor so it can query the ATS.

Yes. Any agent with the tools in its configuration can execute them. A screener agent might run search_jobs while a scheduler agent checks list_interviews.

No, the MCP standard handles that. When an agent calls get_job_info, the JSON response is automatically converted into a conversational format the other agents can read.

Tell your primary agent to run get_account_check. It will confirm the credentials are valid before the rest of the group chat starts trying to pull candidate data.

Only your connected AutoGen clients. Vinkius routes the job titles, applicant names, and interview notes through an ephemeral container that destroys itself the moment the tool call finishes.

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