How to Use the Plaud MCP in CrewAI

Q: Do Plaud tools work in sequential CrewAI tasks?

They do. You can pass the output of gettranscript from one agent to the next to complete multi-step analysis.

Deploy autonomous Plaud crews. Specialized agents working together to manage, summarize, and act on your meeting recordings.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Plaud MCP to CrewAI

Create your Vinkius account to connect Plaud to CrewAI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Plaud with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Autonomous Plaud recording crews

Assign an agent to monitor new recordings using `list_files` while another agent processes them with `get_summary`. They share memory to stay updated. It’s a team approach to data management. One agent can focus on categorization while the other handles the actual transcript review.

Intelligent Plaud file organization

Give your crew the power to use `update_file` and `list_tags` to keep your library sorted. They can rename files based on the meeting content they analyze. Your files stay organized without you lifting a finger. The agents follow the rules you set for naming and tagging conventions.

Systematic Plaud transcript analysis

Run hierarchical crews where a manager agent reviews summaries from `get_transcript` before taking action. It ensures quality control across all your meetings. You get a structured output from your entire history. It’s perfect for turning months of meetings into a searchable archive.

Setup guide

Set up Plaud MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Plaud tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Plaud Analyst",
    goal="Access and analyze Plaud data via MCP.",
    backstory="Expert analyst with direct Plaud access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Plaud transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Plaud Analyst",
        goal="Access and analyze Plaud data via MCP.",
        backstory="Expert analyst with direct Plaud access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Plaud transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 Plaud. 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.