How to Use the Flodesk MCP in LangChain

Q: Can I trace Flodesk API calls made by LangChain in LangSmith?

Yes. Every tool call like listworkflows or triggerworkflow is tracked. You can inspect the exact payload, latency, and token usage for every marketing action your agent takes.

Q: Can the agent manage custom email fields?

Yes. The agent can query existing custom attributes with listcustomfields and generate new ones using createcustomfield to store specific user metadata.

Build multi-step email marketing pipelines by connecting your LangChain agents directly to Flodesk subscriber lists and workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Flodesk MCP to LangChain

Create your Vinkius account to connect Flodesk 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 Flodesk with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build deep LangChain workflow chains

Use `list_subscribers` to find inactive users, check their status, and immediately pass those IDs to `unsubscribe_subscriber` in a single run. This isn't just basic scripting. You are building active reasoning chains where the output of one Flodesk tool feeds right into the next step. Use LangSmith to watch the entire execution. You can see exactly how the agent decides to trigger a specific sequence. No more blind API calls. If an agent calls `list_segments` and finds a match, it routes the subscriber there instantly.

Multi-server aggregation for marketing

Pull user records from an external SQL database and pass them directly to `create_subscriber` using a single LangChain client. You don't need to write custom glue code for every single endpoint. The agent handles the data mapping. It reads your database schema, creates the matching custom attributes using `create_custom_field`, and populates them. Your LangChain setup manages the data flow across multiple MCP servers without losing context.

Automated segment triage

Poll your subscriber base using `list_subscribers` and sort them into targeted groups without manual exports. The agent evaluates user activity and runs `add_to_segment` or `trigger_workflow` based on real-time behavior. This turns your static email list into an active, self-sorting system. Your agent handles the logic of who gets what email. You just define the rules, and the LangChain MCP adapter executes the Flodesk updates.

Setup guide

Set up Flodesk 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 Flodesk 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({
    "flodesk-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 Flodesk 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 Flodesk. 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 Flodesk 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 Flodesk MCP in LangChain

Install the MCP adapter, initialize the client with your Vinkius endpoint, and call get_tools. Pass that array to your agent constructor so it can run tools like `create_subscriber` on its own.

Yes. Every tool call like `list_workflows` or `trigger_workflow` is tracked. You can inspect the exact payload, latency, and token usage for every marketing action your agent takes.

LangChain handles this through standard runnable retry configurations. If `add_to_segment` hits a temporary API limit, the chain backs off and retries automatically before failing.

Yes. The agent can query existing custom attributes with `list_custom_fields` and generate new ones using `create_custom_field` to store specific user metadata.

Vinkius runs this MCP server in an isolated sandbox. Your subscriber emails and custom field data never touch third-party storage. They pass directly between LangChain and Flodesk via encrypted, ephemeral V8 sessions.

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