How to Use the KnowFirst MCP in CrewAI

Q: How can I make two CrewAI agents collaborate using KnowFirst data?

Have one agent use searchintelligenceentities to find a company. It then returns the entity ID as its output. The next agent in the crew takes that ID as input and uses it with getentityprofile to continue the work.

Q: Can I build a CrewAI team to find new data sources with KnowFirst?

Yes. Assign one agent the task of periodically running listintelligencesources. A second agent can then take that list and use searchdatasources to dig deeper into specific source types, like social signals or public records.

Q: How do I pass KnowFirst credentials to my agents in CrewAI?

CrewAI handles this through the MCPServerHTTP class or by passing the full Vinkius endpoint URL directly in the agent's mcps parameter. The framework manages the connection and authentication for your whole crew.

Deploy an autonomous crew of AI agents to research, analyze, and report on market intelligence using KnowFirst.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect KnowFirst MCP to CrewAI

Create your Vinkius account to connect KnowFirst 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 KnowFirst with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble an Autonomous Research Crew

With CrewAI, you assign specific KnowFirst tools to different agents. Give a 'Researcher' agent access to `search_intelligence_entities` and `get_entity_profile`. An 'Analyst' agent gets `get_entity_connections` and `list_entity_data_points`. The Researcher finds a target company, then passes the entity ID to the Analyst. The Analyst maps its network and analyzes the raw data, passing a summary to a 'Writer' agent. It's a full assembly line for intelligence reports.

Run Continuous Market Monitoring Teams

Set up a CrewAI team for 24/7 monitoring. One agent's only job is to run `get_market_intelligence_trends` every hour. If it detects a significant new trend, it adds the finding to the crew's shared memory. A second agent monitors that memory. When a new trend appears, it triggers a task for another agent to investigate using `search_intelligence_entities`. This is how you build a system that reacts to market changes on its own, using one MCP server for all tools.

Specialize Agents with CrewAI Tool Filtering

CrewAI's `tool_filter` lets you create highly specialized agents. A 'Compliance' agent might only have access to the `audit_entity_changes` tool. A 'Prospecting' agent might only use `search_data_sources` to find new leads. This separation of duties makes your autonomous system more robust and secure. You're not giving one agent the keys to everything. You're building a team where each member has a specific, limited job, powered by KnowFirst.

Setup guide

Set up KnowFirst 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 KnowFirst tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Have one agent use `search_intelligence_entities` to find a company. It then returns the entity ID as its output. The next agent in the crew takes that ID as input and uses it with `get_entity_profile` to continue the work.

Yes. Assign one agent the task of periodically running `list_intelligence_sources`. A second agent can then take that list and use `search_data_sources` to dig deeper into specific source types, like social signals or public records.

CrewAI handles this through the `MCPServerHTTP` class or by passing the full Vinkius endpoint URL directly in the agent's `mcps` parameter. The framework manages the connection and authentication for your whole crew.

Competitive analysis is a perfect fit. You can have one agent track a competitor's profile changes with `audit_entity_changes`, another analyze their network with `get_entity_connections`, and a third summarize the findings into a daily briefing.

Your queries and the resulting intelligence profiles are transient. The server processes them in an ephemeral V8 Isolate and doesn't log or retain the content. Each CrewAI agent's request is a discrete, stateless transaction secured by TLS.

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