How to Use the Fellow MCP in LangChain

Q: Can a LangChain chain assign a Fellow task to a specific engineer?

Yes, the createactionitem tool accepts an email address parameter. Your LangChain agent can search your workspace directory using listusers to find the correct email, then feed that directly into the creation tool.

Q: Can I use this to summarize old meeting notes?

Yes, you use getnote to fetch the raw text of any specific doc. From there, your agent processes the content through your preferred LLM to generate concise summaries or highlight technical decisions.

Run your meeting agendas and assign follow-ups directly through your LangChain chains without touching a browser.

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

Chain Meeting Context to Code

The `list_meetings` tool fetches your recent Fellow syncs so your LangChain agent can analyze what your team discussed. This tool feeds raw meeting metadata directly into your subsequent chain steps, allowing the LLM to extract key decisions without manual copy-pasting. You trace these operations through LangSmith to monitor latency and token costs for every meeting retrieval. If a developer asks for context on a project, your chain pulls the data, matches it with code commits, and outputs a clear summary.

Automate Action Items inside LangChain

The `create_action_item` tool registers new tasks in your Fellow workspace directly from your LangChain multi-step reasoning pipelines. Your agent evaluates code review comments or Slack alerts, decides a task is necessary, and runs this tool with a specific due date and owner email. Because LangChain handles multi-server aggregation, you can combine this MCP tool with your GitHub or Jira steps. The agent writes the code, opens the pull request, and instantly logs the corresponding action item in Fellow.

Track Progress with LangChain MCP Server Tools

The `list_action_items` tool pulls your team's pending tasks so your LangChain agent can audit project status. By filtering for "pending" or "completed" states, the agent matches outstanding work against current sprint milestones. You build stateless chains that inspect these tasks and notify team members of overdue items. Using LangChain's structured output, the retrieved task list maps directly to your custom internal reporting dashboards.

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-alternative-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

You pass your Vinkius endpoint token to the LangChain MultiServerMCPClient setup. This single MCP connection handles the connection to the Fellow API, so your agent can run `list_meetings` immediately without managing separate OAuth flows.

Yes, the `create_action_item` tool accepts an email address parameter. Your LangChain agent can search your workspace directory using `list_users` to find the correct email, then feed that directly into the creation tool.

LangChain's runnable chains let you configure retry logic and rate limiters directly on the tool calls. If your workspace has hundreds of weekly syncs, this prevents `list_notes` from hitting API throttling limits.

Yes, you use `get_note` to fetch the raw text of any specific doc. From there, your agent processes the content through your preferred LLM to generate concise summaries or highlight technical decisions.

This MCP Server isolates all meeting notes, streams, and action items inside Vinkius's secure V8 Isolate Sandbox. The server only reads the specific notes you request via `get_note`, and your raw workspace data never persists on our servers after the execution completes.

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