How to Use the TrueFoundry MCP in LangChain

Q: What happens if my TrueFoundry deployment fails?

You check the failure point using truefoundrygetdeploymentstatus. If it's down, your LangChain agent can be programmed to retry or pivot to a backup plan immediately. It keeps the whole pipeline from failing over one bad call.

Q: Can TrueFoundry connect my multi-server chain?

Yes. By listing available MCP tools using truefoundrylistmcpservers, you get a complete registry of all logical tools across the entire TrueFoundry environment, letting your LangChain agent treat them as one pool.

Q: How do I manage different model versions with TrueFoundry and LangChain?

You use truefoundrylistgatewaymodels to pull a definitive list of all accessible foundation models. Your agent then decides which one to pass to the gateway via truefoundryrungatewaychat for the best result.

Q: What data type does TrueFoundry expose regarding deployment status?

The truefoundrygetdeploymentstatus tool emits detailed metric states on the orchestration matrix bounds, giving you hard data on container health and resource allocation.

Build multi-step reasoning agents with LangChain and TrueFoundry.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect TrueFoundry MCP to LangChain

Create your Vinkius account to connect TrueFoundry 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 TrueFoundry with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

TrueFoundry for LangChain: Manage MCP Server deployments.

When your agent needs to run code or interact with a backend service, you spawn it first. Use `truefoundry_deploy_mcp_server` to spin up the necessary container process within the TrueFoundry mesh. You'll then use `truefoundry_get_deployment_status` and `truefoundry_list_deployments` to make sure that service is actually ready before your chain tries to call it.

TrueFoundry for LangChain: Embeddings and Metadata Retrieval.

Your agent needs context beyond just chat history. Call `truefoundry_generate_embeddings` to calculate semantic vectors securely, feeding that data right into the next step of your chain. You can also pull specific tool definitions using `truefoundry_get_mcp_server_info` so your ReAct agent knows exactly what it's allowed to call.

TrueFoundry for LangChain: Dynamic LLM Gateway Calls.

The core of the chain is often talking to a model. Instead of hardcoding an API, use `truefoundry_run_gateway_chat` to push the query through TrueFoundry's unified gateway. This method lets your agent dynamically choose between dozens of proxy models based on the prompt.

Setup guide

Set up TrueFoundry 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 TrueFoundry 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({
    "truefoundry-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 TrueFoundry 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 TrueFoundry. 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 TrueFoundry 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 TrueFoundry MCP in LangChain

TrueFoundry allows you to expose structured tools that are treated as links in your chain. This means your agent doesn't just call the tool; it uses the output from one MCP tool (like `truefoundry_list_mcp_servers`) as the direct input for another, creating a reliable data flow.

You check the failure point using `truefoundry_get_deployment_status`. If it's down, your LangChain agent can be programmed to retry or pivot to a backup plan immediately. It keeps the whole pipeline from failing over one bad call.

Yes. By listing available MCP tools using `truefoundry_list_mcp_servers`, you get a complete registry of all logical tools across the entire TrueFoundry environment, letting your LangChain agent treat them as one pool.

You use `truefoundry_list_gateway_models` to pull a definitive list of all accessible foundation models. Your agent then decides which one to pass to the gateway via `truefoundry_run_gateway_chat` for the best result.

The `truefoundry_get_deployment_status` tool emits detailed metric states on the orchestration matrix bounds, giving you hard data on container health and resource allocation.

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