How to Use the Fellow MCP in Mastra AI

Q: How do I connect the Fellow MCP Server to my Mastra AI agents?

Instantiate MCPClient with your Vinkius HTTP endpoint and register it in your Mastra configuration. Spread the returned tools into your agent's tool array so it can run listmeetings autonomously.

Q: Can Mastra AI automatically resolve tasks in Fellow?

Yes, you can design a workflow where Mastra AI calls completeactionitem once an external codebase pull request is merged. The agent verifies the task ID and updates the status automatically.

Q: Does Mastra AI support human approval before changing Fellow items?

Yes, you can set requireToolApproval on tools like createactionitem or completeactionitem. This pauses the Mastra workflow until a manager approves the proposed task changes.

Q: How do I check API connectivity between Mastra AI and Fellow?

Your workflow can run checkfellowstatus as its initial step before executing heavier data operations. This prevents your agents from running complex logic if the workspace API is temporarily unreachable.

Q: How is my sensitive meeting text protected in Mastra AI?

Your meeting notes retrieved via getnote are processed in memory within Vinkius's zero-trust MCP sandbox. No raw text is stored on external servers, keeping your company's internal discussions confidential.

Automate complex meeting workflows using Mastra AI agents connected to the Fellow MCP Server.

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 Mastra AI

Create your Vinkius account to connect Fellow to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger multi-step workflows from Fellow updates

`list_action_items` allows your Mastra AI agent to scan for pending tasks across your entire team workspace. The agent evaluates the status of each item and initiates conditional branching based on overdue dates. If a task is past due, the workflow automatically calls `get_action_item` to fetch assignee details. Mastra then executes retry logic to alert the owner without manual intervention.

Sync recurring series using this MCP Server

`list_streams` exposes your recurring meeting series directly to Mastra AI's workflow engine. You can build automated pipelines that trigger every time a new stream is detected in your workspace. By combining this with `get_stream`, your agent checks the metadata of your recurring syncs via the MCP Server. Mastra handles failures gracefully with exponential backoff if the platform API rate limits are hit.

Audit meeting notes with Mastra AI agents

`list_notes` retrieves the documents associated with any meeting ID so your Mastra AI agent can parse them. The agent runs analysis on the text to identify unlogged tasks. When missing tasks are found, the agent calls `create_action_item` to insert them back into the workspace. This ensures no decisions are lost between syncs.

Setup guide

Set up Fellow MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Fellow tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "fellow-alternative-mcp-client",
  servers: {
    "fellow-alternative-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Fellow Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Fellow tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Fellow transactions"
);
console.log(result.text);

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 Mastra AI

Instantiate `MCPClient` with your Vinkius HTTP endpoint and register it in your Mastra configuration. Spread the returned tools into your agent's tool array so it can run `list_meetings` autonomously.

Yes, you can design a workflow where Mastra AI calls `complete_action_item` once an external codebase pull request is merged. The agent verifies the task ID and updates the status automatically.

Yes, you can set `requireToolApproval` on tools like `create_action_item` or `complete_action_item`. This pauses the Mastra workflow until a manager approves the proposed task changes.

Your workflow can run `check_fellow_status` as its initial step before executing heavier data operations. This prevents your agents from running complex logic if the workspace API is temporarily unreachable.

Your meeting notes retrieved via `get_note` are processed in memory within Vinkius's zero-trust MCP sandbox. No raw text is stored on external servers, keeping your company's internal discussions confidential.

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