Can my agent retrieve the AI summary of a specific Granola meeting?

Yes. Use the 'get_summary' tool. The agent will fetch the native generative results, reducing the bulk meeting content into synthesized blocks and key takeaways flawlessly.

How do I extract action items from recorded notes via chat?

Use the 'get_action_items' tool. Your agent will isolate targeted steps inferred from the meeting intent, enabling you to automate your post-meeting follow-up workflows natively.

Can I search for meetings from a specific date range through the agent?

Absolutely. Use the 'list_by_date' tool. Provide the start and end dates in ISO 8601 format. The agent will trigger temporal scoping routines to expose specific documents mapped historically.

Granola MCP Server for CrewAI 12 tools — connect in under 2 minutes

Name: Granola
Availability: InStock
Author: Vinkius

docs.crewai.com/mcp/overview

Built by Vinkius GDPR 12 Tools Framework

Connect your CrewAI agents to Granola through Vinkius, pass the Edge URL in the `mcps` parameter and every Granola tool is auto-discovered at runtime. No credentials to manage, no infrastructure to maintain.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from crewai import Agent, Task, Crew

agent = Agent(
    role="Granola Specialist",
    goal="Help users interact with Granola effectively",
    backstory=(
        "You are an expert at leveraging Granola tools "
        "for automation and data analysis."
    ),
    # Your Vinkius token. get it at cloud.vinkius.com
    mcps=["https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"],
)

task = Task(
    description=(
        "Explore all available tools in Granola "
        "and summarize their capabilities."
    ),
    agent=agent,
    expected_output=(
        "A detailed summary of 12 available tools "
        "and what they can do."
    ),
)

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

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Granola MCP Server

Connect your Granola.ai account to any AI agent and take full control of your AI-powered meeting notes, searchable conversation memory, and automated summaries through natural conversation.

When paired with CrewAI, Granola becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Granola tools autonomously, one agent queries data, another analyzes results, a third compiles reports, all orchestrated through Vinkius with zero configuration overhead.

What you can do

Meeting Document Orchestration — List all meeting documents in your workspace and retrieve primary entry points for workspace interactions natively
Live Content Retrieval — Access full structured content of meeting documents, parsing human-modified annotations and ML-generated notes flawlessy
AI Summarization — Retrieve synthesized AI-generated blocks reducing bulk meeting content into concise overviews and key takeaway nodes limitlessly
Action Item Tracking — Isolate specifically categorized target steps inferred from recorded meeting intent to automate post-meeting follow-ups
Transcript Auditing — Retrieve full speaker-detected transcripts parsed locally on device, containing semantic and chronological speech metadata natively
Participant Navigation — Identify meeting attendees by cross-referencing calendar arrays bound to Granola sessions synchronously
Global Workspace Search — Execute full-text term detection across all documents to find specific discussions and prioritized ranked datasets
Folder & List Management — Enumerate high-level categorization labels grouping documents physically inside directories to browse your workspace hierarchy
Batch Retrieval Oversight — Fetch multiple meeting documents by their IDs in a single request to analyze complex cross-meeting dependencies securely

The Granola MCP Server exposes 12 tools through the Vinkius. Connect it to CrewAI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Granola to CrewAI via MCP

Follow these steps to integrate the Granola MCP Server with CrewAI.

Install CrewAI

Run pip install crewai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Customize the agent

Adjust the role, goal, and backstory to fit your use case

Run the crew

Run python crew.py. CrewAI auto-discovers 12 tools from Granola

Why Use CrewAI with the Granola MCP Server

CrewAI Multi-Agent Orchestration Framework provides unique advantages when paired with Granola through the Model Context Protocol.

Multi-agent collaboration lets you decompose complex workflows into specialized roles, one agent researches, another analyzes, a third generates reports, each with access to MCP tools

CrewAI's native MCP integration requires zero adapter code: pass Vinkius Edge URL directly in the `mcps` parameter and agents auto-discover every available tool at runtime

Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls

Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports

Granola + CrewAI Use Cases

Practical scenarios where CrewAI combined with the Granola MCP Server delivers measurable value.

Automated multi-step research: a reconnaissance agent queries Granola for raw data, then a second analyst agent cross-references findings and flags anomalies. all without human handoff

Scheduled intelligence reports: set up a crew that periodically queries Granola, analyzes trends over time, and generates executive briefings in markdown or PDF format

Multi-source enrichment pipelines: chain Granola tools with other MCP servers in the same crew, letting agents correlate data across multiple providers in a single workflow

Compliance and audit automation: a compliance agent queries Granola against predefined policy rules, generates deviation reports, and routes findings to the appropriate team

Granola MCP Tools for CrewAI (12)

These 12 tools become available when you connect Granola to CrewAI via MCP:

get_action_items

Extract action items identified from a meeting document

get_content

Retrieve the full structured content of a meeting document

get_documents_batch

Fetch multiple documents by their IDs in a single request

get_metadata

Retrieve metadata for a specific meeting document

get_participants

Retrieve the list of participants for a specific meeting

get_summary

Retrieve the AI-generated summary of a meeting document

get_transcript

Retrieve the full transcript of a meeting with speaker detection

list_by_date

List meeting documents within a specific date range

list_documents

List all meeting documents in the Granola workspace with pagination

list_folders

List all document lists (folders) in the Granola workspace

list_recent

List the 20 most recent meeting documents

search_documents

Full-text search across all meeting documents

Example Prompts for Granola in CrewAI

Ready-to-use prompts you can give your CrewAI agent to start working with Granola immediately.

"Show me the 5 most recent meeting documents"

"What were the action items from meeting 'abc-123'?"

"Search for meeting notes mentioning 'competitor analysis'"

Troubleshooting Granola MCP Server with CrewAI

Common issues when connecting Granola to CrewAI through the Vinkius, and how to resolve them.

MCP tools not discovered

Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts. check console output.

Agent not using tools

Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".

Timeout errors

CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.

Rate limiting or 429 errors

Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.

Granola + CrewAI FAQ

Common questions about integrating Granola MCP Server with CrewAI.

How does CrewAI discover and connect to MCP tools?

CrewAI connects to MCP servers lazily. when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.

Can different agents in the same crew use different MCP servers?

Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.

What happens when an MCP tool call fails during a crew run?

CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.

Can CrewAI agents call multiple MCP tools in parallel?

CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.

Can I run CrewAI crews on a schedule (cron)?

Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.