How to Use the Nylas MCP in CrewAI

Q: How do I expose specific Nylas tools to a CrewAI agent?

Use the MCPServerHTTP class from the crewai.mcp package and apply a toolfilter. This lets you restrict a specific CrewAI agent to listmessages while reserving sendmessage for an executive-level agent.

Q: How does CrewAI handle errors when a Nylas calendar event deletion fails?

When deleteevent fails, CrewAI's internal error-handling loop passes the Nylas API exception back to the agent. The agent then analyzes the failure and attempts to find the event again using listevents.

Q: How are my private Nylas emails protected when using CrewAI?

Your email messages and drafts fetched via listmessages and listdrafts remain strictly in local CrewAI agent memory during execution. The Vinkius sandbox ensures all data transmission is encrypted and ephemeral, with zero persistent storage of your mail.

Deploy specialized agent teams to manage your emails and calendar events autonomously using CrewAI and the Nylas 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 Nylas MCP to CrewAI

Create your Vinkius account to connect Nylas 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 Nylas with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-agent Nylas inbox triage pipelines in CrewAI

The `list_messages` tool serves as the primary data source for your CrewAI triage agents. A dedicated researcher agent pulls the unified Nylas inbox stream, while a separate coordinator agent analyzes the content to prioritize urgent threads. By passing this MCP tool to your crew, agents collaborate using shared memory to track which emails have been processed. They can then hand off draft responses to a writer agent who executes `send_message` autonomously via Nylas.

Manage autonomous calendar scheduling crews in CrewAI

The `list_calendars` tool allows a CrewAI scheduling agent to locate active calendar UUIDs across different providers. Once found, the agent coordinates with a calendar auditor to run `list_events` and identify open meeting slots. The final step uses `create_event` to book the meeting, resolving conflicts without human intervention. CrewAI's sequential execution model ensures each step validates against the shared Nylas calendar state before committing.

Let specialized CrewAI agents manage your address book

The `list_contacts` tool enables a CrewAI contact manager agent to audit your address book for duplicates. The agent works alongside a directory assistant that uses `create_contact` to update stale listings. Because CrewAI supports selective MCP tool exposure via `tool_filter`, you can restrict your contact agents to read-only tools while giving write access only to your moderator agent. This keeps your Nylas directory clean and secure.

Setup guide

Set up Nylas 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 Nylas tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Use the `MCPServerHTTP` class from the `crewai.mcp` package and apply a `tool_filter`. This lets you restrict a specific CrewAI agent to `list_messages` while reserving `send_message` for an executive-level agent.

Yes, CrewAI agents share access to the configured Nylas MCP Server tools through their collaborative environment. One agent can query schedules using `list_events` while another schedules a call using `create_event` in parallel.

When `delete_event` fails, CrewAI's internal error-handling loop passes the Nylas API exception back to the agent. The agent then analyzes the failure and attempts to find the event again using `list_events`.

Simply pass the Vinkius HTTP endpoint directly into your CrewAI Agent's `mcps` array parameter. This sets up the MCP connection instantly using stdio or SSE transports without manual server management.

Your email messages and drafts fetched via `list_messages` and `list_drafts` remain strictly in local CrewAI agent memory during execution. The Vinkius sandbox ensures all data transmission is encrypted and ephemeral, with zero persistent storage of your mail.

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