How to Use the Fellow MCP in LangChain

Q: How do I handle human approval before completing a Fellow task in LangChain?

Use LangGraph to pause the chain before it calls completeactionitem. This gives you a chance to verify the work before the agent updates the status.

Q: Can I pipe a Fellow transcript into another API using LangChain?

Yes. You can fetch raw text using gettranscript and immediately pass it to another chain node. This works well for syncing meeting summaries to external databases.

Chain meeting insights directly into your codebase by connecting this Fellow MCP Server to your LangChain agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fellow MCP to LangChain

Create your Vinkius account to connect Fellow 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 Fellow with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track action items in LangChain pipelines

Use `list_action_items` to pull active tasks directly into your ReAct chains. Your agent can inspect a specific task with `get_action_item` and decide the next step based on live code execution. If a task is finished, the agent calls `complete_action_item`. We recommend adding a human-in-the-loop step in LangGraph before executing this to keep team accountability tight.

Run post-meeting analysis with LangSmith tracing

Connect `get_transcript` to your chains to extract key decisions immediately after a call. LangSmith lets you trace exactly how the agent processes the meeting text and which tools it triggers. You can feed the output of `list_notes` into other APIs in your chain. This lets you sync meeting documentation with external systems without manual copy-pasting.

Safe document cleanup via LangChain MCP Server tools

This MCP Server lets your agent clean up workspace clutter using `delete_note` and `delete_recording`. The agent will always prompt for human confirmation before running these destructive actions. You get full visibility into every deletion attempt in your LangSmith dashboard. It keeps your Fellow workspace clean while protecting important documentation from accidental loss.

Setup guide

Set up Fellow 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 Fellow 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({
    "fellow-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 Fellow 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 Fellow. 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 Fellow 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 Fellow MCP in LangChain

Use LangGraph to pause the chain before it calls `complete_action_item`. This gives you a chance to verify the work before the agent updates the status.

Yes. You can fetch raw text using `get_transcript` and immediately pass it to another chain node. This works well for syncing meeting summaries to external databases.

You initialize the MultiServerMCPClient with the Vinkius endpoint. It aggregates all tools so your agent can query Fellow alongside your other databases.

Turn on LangSmith tracing to inspect the exact inputs and outputs of tools like `list_notes` or `get_recording`. You will see the raw API responses in real time.

Your meeting transcripts, notes, and recordings stay inside Vinkius's secure sandboxed environment. The MCP Server only fetches data when your chain explicitly requests it, and credentials never touch client-side logs.

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