How to Use the Apideck MCP in LangChain

Q: Can LangChain trace Apideck payload sizes in LangSmith?

Yes, every call to listcrmcontacts or executeproxy shows up as a standard tool run. You can inspect the exact JSON payloads and latency inside your LangSmith dashboard.

Run your LangChain agents across dozens of CRMs with a single Apideck integration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Apideck MCP to LangChain

Create your Vinkius account to connect Apideck 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 Apideck with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain CRM pipelines in LangChain

Your LangChain agent can now pull contacts from Salesforce or HubSpot using `list_crm_contacts` and feed that data directly into the next step of your chain. You don't have to write custom glue code for every single CRM vendor on the market. LangSmith traces the entire flow so you see exactly how the agent maps fields. If a run fails, you can pinpoint whether the error came from the Apideck MCP Server or your prompt logic.

Manage customer vaults on the fly

Give your agents the ability to authenticate users by calling `create_vault_session` mid-run. This lets your LangChain pipeline spin up secure integration settings without hardcoding secrets. You can keep track of active pipelines with `list_vault_connections` to see which platforms your users have linked. The agent handles the API handshake, keeping your core chain clean.

Execute raw proxy calls through MCP Server

When unified endpoints don't cover a niche field, your LangChain agent uses `execute_proxy` to hit the downstream API directly. This keeps your agentic workflow from hitting a brick wall when a customer asks for a custom property. This setup avoids the headache of importing ten different SDKs into your Python environment. You get one tool that routes requests to any platform Apideck supports.

Setup guide

Set up Apideck 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 Apideck 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({
    "apideck-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 Apideck 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 Apideck. 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 Apideck 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 Apideck MCP in LangChain

Install the adapter and initialize the client with the Vinkius URL. Pass the tools from the MCP connection directly to your stateful agent graph.

Yes, every call to `list_crm_contacts` or `execute_proxy` shows up as a standard tool run. You can inspect the exact JSON payloads and latency inside your LangSmith dashboard.

Yes, the tools themselves are stateless, but you can wrap the client in a session to maintain connection states. This lets your agent remember which Vault session it opened in previous steps.

The server catches the downstream error and returns a clean error message to your agent. Your agent can then decide to retry or notify the user.

Your CRM contacts and API keys never touch Vinkius disks. All raw data passes through a secure, ephemeral sandbox that processes the request and immediately clears memory.

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