How to Use the Ashby MCP in LangChain

Q: Can LangChain agents search Ashby candidates by name?

Yes. The agent calls searchcandidates with the name or email. The JSON response feeds right back into the chain's memory for the next reasoning step.

Build multi-step recruiting pipelines in LangChain. Your agents read Ashby data, decide next steps, and trigger actions automatically.

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 LangChain

Create your Vinkius account to connect Ashby to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Wire this MCP Server into LangChain

ReAct agents need real-time data to make hiring decisions. When you connect this server, your LangGraph setup gets direct access to the ATS. You write the prompt, and the agent decides when to pull records. A typical chain might start with `search_candidates` to find an applicant by email. The output feeds straight into `get_candidate_info` to pull their full resume history, followed by `list_interviews` to check their current pipeline stage. LangSmith tracks every token spent on these requests.

Filter open roles dynamically

Static job boards require constant manual updates. Your AI client can handle that automatically by querying the system on a schedule. It pulls active listings and feeds them into downstream summarization tasks. Trigger `list_jobs` with status filters to grab only published positions. If an agent spots a missing detail in the payload, it fires `get_job_info` to pull the complete description before passing the combined context to your database.

Track candidate progress

Recruiters waste hours clicking through tabs to find where someone sits in the funnel. You can build a custom tool that fetches this instantly. The agent handles the API calls while you focus on the actual conversation. Call `list_applications` to dump the current active queue. When a specific ID catches the agent's attention, it runs `get_application_info` to read the exact status and notes attached to that profile.

Setup guide

Set up Ashby MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Ashby tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "ashby-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Ashby transactions"
    })
    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 LangChain

Install the langchain-mcp-adapters package. Setup a MultiServerMCPClient pointing to your Vinkius endpoint, then pass the tools from client.get_tools() straight into your ReAct agent.

Yes. The agent calls search_candidates with the name or email. The JSON response feeds right back into the chain's memory for the next reasoning step.

You skip writing custom API wrappers. The server exposes a standard tool schema that LangChain understands natively, saving you hundreds of lines of boilerplate code.

Every request to the ATS gets logged. You see the exact latency, token usage, and payload for tools like get_job_info right in your LangSmith dashboard.

Vinkius runs your server in a V8 Isolate Sandbox. Candidate emails, interview schedules, and application notes are processed ephemerally and wiped immediately after the response hits your LangChain client.

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