How to Use the Autobound MCP in LangChain

Q: How do I chain Autobound tools together in LangChain?

You pass the tools to an agent created with createagent. The agent then decides which tool to call, like using the output of searchsignals as the input for enrichcontact, creating a dynamic sequence.

Q: Can my LangChain agent generate both emails and LinkedIn messages with Autobound?

Yes. The agent has access to both generateemail and generatelinkedin. You can write logic that lets it choose the right tool based on the prospect's profile or your campaign goals.

Q: What's the best way to start a sales workflow using Autobound and LangChain?

A good starting point is searchsignals. This gives your agent a real buying signal to kick off a research and outreach chain using other Autobound tools like enrichcontact and generateemail.

Build multi-step sales agents that research prospects and write outreach using LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Autobound MCP to LangChain

Create your Vinkius account to connect Autobound 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 Autobound with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Prospect-to-Outreach Chains

Chain Autobound's tools together to create a complete sales workflow. Your LangChain agent can start by calling `search_signals` to find a new buying signal. The output from that tool—a new lead—is then automatically fed into `enrich_contact` to get their details. From there, the chain continues. The enriched contact data becomes the input for `generate_email` or `generate_linkedin`. Once the copy is ready, the agent's final step is to call `execute_campaign`. You're building a full pipeline, from a raw signal to a sent message, all orchestrated by your agent's logic.

Dynamic Sales Research with LangChain

Your agent doesn't have to follow a fixed script. It can decide which Autobound tools to call based on what it finds. For example, it might `list_prospects`, notice one is missing key data, and decide on its own to run `enrich_company`. This is what ReAct agents are for. You can watch the agent's thought process in LangSmith as it weighs whether to check `get_campaign` details or `search_signals` for a fresh opportunity. It's not just running tools; it's actively reasoning about your sales data.

Scale Enrichment Across Your CRM

Stop doing one-off lookups. Use LangChain to build a data pipeline that pulls stale contacts from your database and feeds them into Autobound's `enrich_bulk` tool. It handles the batching and processing for you. Then you can add logic to the chain. After a contact is enriched, check a custom field. If they're a VP, run `generate_linkedin`. If they're a director, run `generate_email`. This MCP Server gives your chains the sales intelligence they need to take the right action.

Setup guide

Set up Autobound 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 Autobound 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({
    "autobound-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 Autobound 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 Autobound. 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 Autobound 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 Autobound MCP in LangChain

You pass the tools to an agent created with `create_agent`. The agent then decides which tool to call, like using the output of `search_signals` as the input for `enrich_contact`, creating a dynamic sequence.

Yes. The agent has access to both `generate_email` and `generate_linkedin`. You can write logic that lets it choose the right tool based on the prospect's profile or your campaign goals.

A good starting point is `search_signals`. This gives your agent a real buying signal to kick off a research and outreach chain using other Autobound tools like `enrich_contact` and `generate_email`.

LangChain agents have built-in error handling. You can configure your chain to retry a failed `enrich_contact` call, or to log the error and simply move on to the next prospect in a list.

Yes. All requests between your LangChain agent and the Autobound MCP Server are sent over HTTPS. The server runs in a Vinkius sandbox, and your token handles auth so you don't expose raw credentials. Autobound only processes the specific prospect or company data you send for each tool call.

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