How to Use the Grain MCP in CrewAI

Q: How do I add Grain tools to a CrewAI agent?

Pass the Vinkius MCP Server URL directly into the mcps parameter when defining your CrewAI agent. This grants that specific agent access to tools like getrecording while keeping other agents focused on different tasks.

Q: How do I limit a CrewAI agent to read-only Grain tools?

Use the MCPServerHTTP class from crewai.mcp and define a toolfilter. This lets you expose safe tools like listrecordings to your agents while hiding destructive or write-heavy tools.

Deploy specialized multi-agent teams in CrewAI to analyze Grain meeting records via our 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 Grain MCP to CrewAI

Create your Vinkius account to connect Grain to CrewAI 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 Grain with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate multi-agent meeting analysis in CrewAI

The `get_transcript` tool allows a specialized "Researcher Agent" in your CrewAI setup to ingest full meeting transcripts. While this agent extracts raw facts, a separate "Editor Agent" can use the transcript to draft follow-up emails and executive summaries. This division of labor prevents a single LLM context window from becoming overwhelmed. CrewAI's shared memory ensures both agents stay aligned on the meeting's core context without redundant API calls.

Extract and distribute action items autonomously

The `get_action_items` tool lets a "Project Manager Agent" in CrewAI pull assigned tasks directly from your Grain recordings via the MCP Server. The agent can then assign these tasks to team members in external project boards based on speaker names. By using CrewAI's hierarchical process, a "Quality Assurance Agent" can review these action items against the original transcript before they are finalized. This multi-step validation ensures high accuracy.

Categorize workspace meetings using CrewAI agents

The `list_tags` tool provides your CrewAI agents with the taxonomy needed to organize your meeting library. A "Librarian Agent" can fetch active tags and apply them to newly uploaded recordings to keep your workspace organized. If a new meeting doesn't fit existing tags, the agent can use `upload_video` to ingest external recordings and tag them appropriately. This keeps your team's video knowledge base indexed and searchable via the MCP Server.

Setup guide

Set up Grain 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 Grain tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Grain 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="Grain Analyst",
        goal="Access and analyze Grain data via MCP.",
        backstory="Expert analyst with direct Grain access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Grain 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 Grain. 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 Grain 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 Grain MCP in CrewAI

Pass the Vinkius MCP Server URL directly into the `mcps` parameter when defining your CrewAI agent. This grants that specific agent access to tools like `get_recording` while keeping other agents focused on different tasks.

Yes, CrewAI agents can share tools or use them independently. For example, your research agent can use `search_recordings` while your analyst agent runs `get_insights` on the results.

Use the `MCPServerHTTP` class from `crewai.mcp` and define a `tool_filter`. This lets you expose safe tools like `list_recordings` to your agents while hiding destructive or write-heavy tools.

Yes, CrewAI supports stdio, SSE, and HTTP transports. You can run the server locally during development or connect to a hosted endpoint on Vinkius for production-grade multi-agent deployments.

All meeting transcripts and action items retrieved from Grain are kept strictly within your local CrewAI process memory. No data is stored externally, and all communication with the MCP Server is encrypted via HTTPS.

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