How to Use the Eden AI MCP in LangChain

Q: Can LangChain trace the latency of Eden AI tool calls?

Yes, every call to getapiusagestatistics shows up in LangSmith with full latency and input parameters. You get complete visibility into how your LangChain agent interacts with the unified Eden AI platform.

Q: How does LangChain handle multi-provider fallbacks with Eden AI?

Your LangChain agent can chain listaiproviders with your LLM configuration to dynamically route requests. If a provider is down, the agent queries the Eden AI MCP server for a working alternative and updates the chain state.

Give your LangChain agents direct access to the Eden AI platform to monitor costs and manage multi-provider workflows in real time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Eden AI MCP to LangChain

Create your Vinkius account to connect Eden AI 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 Eden AI with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build cost-aware LangChain routing pipelines

Your LangChain ReAct agent can now check live Eden AI pricing before executing any step. By calling `get_ai_feature_pricing` directly inside your LangChain chain, the agent decides which Eden AI provider fits your budget on the fly. This prevents surprise bills from Eden AI during recursive LangChain runs. You can feed these Eden AI metrics directly into LangSmith to trace exact LangChain token costs. The LangChain agent runs `get_api_usage_statistics` to log the actual spend of that specific Eden AI workflow execution.

Dynamic provider switching in LangChain chains

When a primary model fails, your LangChain chain needs an immediate Eden AI fallback. This MCP server lets your LangChain agent call `list_ai_providers` to find alternative Eden AI vendors for the exact feature it needs. It keeps your LangChain pipeline running without hardcoding backup Eden AI endpoints. The LangChain agent uses `quick_ai_provider_audit` to get a quick health score of text analysis options in Eden AI. It can swap the underlying Eden AI provider in the next LangChain link based on real-time availability.

Automate workflow deployment via LangChain agents

Stop writing custom LangChain integration code for every new Eden AI automation. Your LangChain agent uses `list_ai_workflows` to fetch your active pipelines and `get_workflow_configuration` to inspect their exact Eden AI steps directly inside the execution context. This means your LangChain app can trigger and configure complex Eden AI automations based on user chat inputs. It uses `list_latest_ai_automations` to check if a background Eden AI task finished before moving to the next LangChain step.

Setup guide

Set up Eden AI 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 Eden AI 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({
    "eden-ai-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 Eden AI 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 Eden AI. 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 Eden AI 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 Eden AI MCP in LangChain

Use the LangChain MCP adapter to fetch the tools and pass them to your agent constructor. The LangChain agent will automatically see Eden AI tools like `list_all_llm_models` and decide when to call them.

Yes, every call to `get_api_usage_statistics` shows up in LangSmith with full latency and input parameters. You get complete visibility into how your LangChain agent interacts with the unified Eden AI platform.

Your LangChain agent can chain `list_ai_providers` with your LLM configuration to dynamically route requests. If a provider is down, the agent queries the Eden AI MCP server for a working alternative and updates the chain state.

Yes, this MCP server is stateless by default, making it perfect for standard LangChain runnable chains. If you need persistent Eden AI context across multiple steps, use the client session wrapper during initialization.

Your Eden AI API keys and workflow configurations never pass through the LLM itself. The MCP server runs in a secure sandbox on Vinkius, exposing only clean tool schemas to your LangChain agent.

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