How to Use the Sansan MCP in CrewAI

Q: Can different CrewAI agents use different Sansan tools?

Yes. You assign searchbizcards to a researcher agent and listpersons to an auditor agent. Using the tool filter ensures agents stick to their specific roles without hallucinating capabilities.

Deploy autonomous agent teams in CrewAI to research business cards via the Sansan MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sansan MCP to CrewAI

Create your Vinkius account to connect Sansan 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 Sansan with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

CrewAI teams analyze network data

The `search_biz_cards` tool allows your primary researcher agent to hunt down specific contacts by name. You assign this tool to a dedicated data-gathering role within your crew. The agent queries the database, extracts the relevant business cards, and passes the raw text to an analyst agent for processing. You restrict the researcher to read-only queries using the tool_filter configuration in the MCPServerHTTP class. The MCP Server processes the search while your moderator agent watches the session. This hierarchical execution ensures one agent finds the data while another decides what to do with it.

Cross-reference corporate hierarchies

The `list_departments` tool gives your organizational mapping agent direct access to corporate structures. It pulls the department list and hands it to a secondary agent equipped with `list_users`. The crew works together to build a complete map of internal employees and their respective divisions. Calling `get_person` lets a specialized verification agent cross-check individual contact details against the broader department map. They operate sequentially. The first agent builds the map, the second verifies the people, and the final agent outputs a clean, validated directory without human input.

Sort incoming contacts autonomously

The `list_tags` tool provides your sorting agent with the existing taxonomy for scanned cards. The agent reads the tags, then uses `list_biz_cards` to pull the uncategorized backlog. It determines which tags apply to which contacts based on job titles and company names. You run this crew on a schedule to keep your contact database organized. The framework handles the shared memory between the sorting agent and the database. You define the roles, provide the tools, and let the agents execute the classification pipeline.

Setup guide

Set up Sansan 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 Sansan tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass the endpoint URL directly into the mcps array when defining your agent. For granular control, import MCPServerHTTP from crewai.mcp and specify exactly which tools the agent can access.

Yes. You assign search_biz_cards to a researcher agent and list_persons to an auditor agent. Using the tool filter ensures agents stick to their specific roles without hallucinating capabilities.

Yes. You configure a manager agent to oversee the process. The manager delegates tasks to worker agents who execute the tool calls, then reviews their output before finalizing the workflow.

The server supports standard HTTP transport. Your Python script connects directly to the endpoint, making it ideal for background crew operations running on a server or locally.

The connection transfers raw OCR text, job titles, and email addresses. Vinkius secures this transit using a zero-trust architecture that drops the connection state immediately. Your contact details never touch a persistent disk on our end.

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