How to Use the R2R MCP in CrewAI

Q: How do I run a search in R2R with CrewAI?

Include the search tool in your agent definition. The crew will invoke this whenever it needs to find specific information within your R2R vector space.

Q: Can I list collections in R2R using CrewAI?

You call listcollections to allow the agent to see all available data sets. This lets the crew decide which collection contains the right answers.

Deploy a CrewAI crew with R2R access. Let your agents perform vector searches and document management autonomously across your operations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect R2R MCP to CrewAI

Create your Vinkius account to connect R2R 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 R2R with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous RAG operations in CrewAI

Assign the `rag_query` tool to your research agent. It will fetch the necessary context from your R2R instance and pass it to the writer agent. This creates a loop where agents collaborate on data they retrieve themselves. You define the goal, and the crew handles the document interaction.

Coordinate document management with CrewAI

Use `list_documents` and `get_document` to let a moderator agent manage your knowledge base. It can audit your R2R files while other agents perform tasks. This keeps your data organized without you lifting a finger. Your agents act as both the researchers and the librarians for your documents.

Monitor R2R MCP Server with CrewAI

Add a monitor agent that periodically calls `get_health`. If the R2R MCP Server reports an error, the agent can pause the crew's execution to prevent bad data usage. This keeps your autonomous operations stable. You aren't just running agents; you are running a self-healing system.

Setup guide

Set up R2R 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 R2R tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="R2R Analyst",
    goal="Access and analyze R2R data via MCP.",
    backstory="Expert analyst with direct R2R access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent R2R 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="R2R Analyst",
        goal="Access and analyze R2R data via MCP.",
        backstory="Expert analyst with direct R2R access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent R2R 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 R2R. 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 R2R 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 R2R MCP in CrewAI

Include the `search` tool in your agent definition. The crew will invoke this whenever it needs to find specific information within your R2R vector space.

Yes. Only the agent authorized for the task accesses your R2R data. All communication is scoped to the specific tools you expose to the crew.

You call `list_collections` to allow the agent to see all available data sets. This lets the crew decide which collection contains the right answers.

CrewAI agents throw an exception which you can handle using a custom task callback. You can stop the crew or reassign the task to another agent.

By using selective tool filtering, you ensure that only the necessary R2R MCP Server tools are exposed. Your raw data remains protected behind the R2R API.

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