How to Use the Guru MCP in CrewAI

Q: How do I expose Guru MCP tools to a CrewAI agent?

Pass your Vinkius endpoint URL directly into the agent's mcps list during initialization. CrewAI automatically discovers and registers the tools for that specific agent.

Q: Can multiple CrewAI agents use Guru tools at the same time?

Yes. Your research agent can run searchknowledgebase while your coordinator agent uses getcarddetails to analyze the content simultaneously.

Q: How does CrewAI manage access permissions in Guru?

Agents use listaccessgroups to check group memberships before sharing or updating sensitive documentation. This prevents agents from exposing restricted cards.

Run teams of specialized CrewAI agents to manage, audit, and search your Guru knowledge base.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Guru MCP to CrewAI

Create your Vinkius account to connect Guru 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 Guru with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative knowledge auditing

The `search_knowledge_base` tool lets a research agent scan for documentation gaps while a writer agent drafts updates. Managing a massive wiki is too much for one agent. Once the researcher identifies a missing piece of info, the writer uses `create_knowledge_card` to fill the gap. They work together in sequence to keep your team's documentation complete.

Autonomous workspace moderation via MCP Server

Use `list_workspace_members` to monitor who has access to specific boards and keep your workspace secure. Keeping your team workspace organized requires constant oversight. This MCP Server gives your autonomous crew the exact tools they need to maintain security compliance. If the agent detects unauthorized or outdated access patterns, it flags them for review.

Automated card lifecycle management

The `list_knowledge_cards` tool lets a monitoring agent find stale entries and pass them to an editor agent. Let your agents handle the tedious work of keeping documentation fresh. The editor agent then gathers new data and runs `update_knowledge_card` to refresh the content. If a card is no longer relevant, it uses `delete_knowledge_card` to archive it.

Setup guide

Set up Guru 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 Guru tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass your Vinkius endpoint URL directly into the agent's `mcps` list during initialization. CrewAI automatically discovers and registers the tools for that specific agent.

Yes. Your research agent can run `search_knowledge_base` while your coordinator agent uses `get_card_details` to analyze the content simultaneously.

Agents use `list_access_groups` to check group memberships before sharing or updating sensitive documentation. This prevents agents from exposing restricted cards.

No. The MCP Server exposes everything natively. Your agents can call tools like `list_knowledge_boards` out of the box without any extra coding.

Your wiki cards, board structures, and search logs are protected by Vinkius's zero-trust gateway. Every request runs in an isolated, short-lived session, ensuring your proprietary company knowledge remains strictly 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