How to Use the Cognita (RAG Framework) MCP in CrewAI

Q: How do I share Cognita (RAG Framework) tools across multiple CrewAI agents?

You pass the MCP Server URL directly into the mcps array when defining your CrewAI agents. This gives both your researcher and writer agents access to tools like ragquery and searchchunks for collaborative RAG tasks.

Q: Can a CrewAI agent autonomously provision directories in Cognita (RAG Framework)?

Yes, a specialized data-ingestion agent can invoke the ingestdata tool to provision JSON payloads and create resource directories. The agent then shares the resulting directory paths with the rest of the crew via shared memory.

Q: How do I restrict which Cognita (RAG Framework) tools a CrewAI agent can use?

You use the MCPServerHTTP class from crewai.mcp and apply a toolfilter. This lets you restrict sensitive tools like ingestdata to your supervisor agent while letting worker agents run ragquery.

Deploy multi-agent teams using CrewAI to run autonomous Cognita (RAG Framework) search and ingestion pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cognita (RAG Framework) MCP to CrewAI

Create your Vinkius account to connect Cognita (RAG Framework) 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 Cognita (RAG Framework) with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent RAG collaboration with CrewAI

The `rag_query` tool allows your specialized CrewAI research agent to query Cognita's active transformation vectors while a separate writer agent compiles the report. This role-based division of labor ensures your agents don't get bogged down with raw vector data and focus only on synthesized outputs. By exposing this MCP Server to your crew, agents can pass the results of `search_chunks` among themselves. A moderator agent can inspect the active presets and pass refined query parameters to the researcher agent for a second pass.

Autonomous ingestion and tracing crews

The `ingest_data` tool lets a dedicated ingestion agent provision highly-available JSON payloads and establish new resource directories without human intervention. While that agent runs, a supervisor agent can call `get_collection` to monitor cloud logging traces and catch payload errors. This setup lets you build autonomous data pipelines where one agent collects raw files, another runs the ingestion, and a third verifies the active bucket properties using `list_data_sources`.

Hierarchical index routing in CrewAI

The `list_collections` tool helps a CrewAI manager agent identify bounded routing spaces inside your Headless Cognita RAG limits. The manager agent inspects these spaces and dynamically assigns specific tasks to sub-agents based on which vector collection contains the relevant data. Your agents can also query `list_models` to check deep internal arrays and mitigate picture constraints. This ensures the crew always selects the optimal model configuration before launching a multi-step RAG extraction task.

Setup guide

Set up Cognita (RAG Framework) 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 Cognita (RAG Framework) tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

    task = Task(
        description="List recent Cognita (RAG Framework) 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 Cognita. 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 Cognita (RAG Framework) 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 Cognita (RAG Framework) MCP in CrewAI

You pass the MCP Server URL directly into the `mcps` array when defining your CrewAI agents. This gives both your researcher and writer agents access to tools like `rag_query` and `search_chunks` for collaborative RAG tasks.

Yes, a specialized data-ingestion agent can invoke the `ingest_data` tool to provision JSON payloads and create resource directories. The agent then shares the resulting directory paths with the rest of the crew via shared memory.

You use the `MCPServerHTTP` class from `crewai.mcp` and apply a `tool_filter`. This lets you restrict sensitive tools like `ingest_data` to your supervisor agent while letting worker agents run `rag_query`.

It supports stdio, SSE, and Streamable HTTP. For production crews running on distributed servers, using Streamable HTTP via Vinkius is the most reliable way to maintain persistent MCP connections.

No. All active transformation vectors and JSON payloads are processed in an ephemeral, zero-trust V8 Isolate sandbox. Vinkius acts as a secure proxy, executing your MCP tools without persisting any of your sensitive RAG data.

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