How to Use the SketricGen MCP in CrewAI

Q: Can I scope a workflow in SketricGen with crewai?

Yes. You run targeted processes using runworkflowwithcontact. This allows the entire team's effort to focus only on information relevant to one specific individual or client.

Q: Can I delete sensitive data using SketricGen with crewai?

Yes. If you need to clear out old records for compliance, deleteconversation lets your agent team wipe entire chat threads from the system's history.

Run autonomous, multi-agent teams with SketricGen using crewai's specialized roles.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect SketricGen MCP to CrewAI

Create your Vinkius account to connect SketricGen 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 SketricGen with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Orchestrate Specialized Agent Teams

CrewAI doesn't just run one agent; it runs a whole team. The MCP Server makes this easy by exposing tools that specialized agents can call—for instance, an 'Analyst Agent' might use `get_knowledge_base` to gather facts. The workflow engine manages the handoff: Analyst gives data, Researcher processes it, and finally, the Manager writes the report.

Environment Setup and Management

Before your agents start collaborating, they need context. You can use `list_knowledge_bases` to see what sources are available or define new ones via the MCP Server's management tools. This keeps all agent communication grounded in verified data. If you run a workflow and it hits a dead end, checking the list of templates (`list_templates`) helps narrow down where the process broke.

Tracking Agent Collaboration Runs

When multiple agents are working together, debugging is messy. Use `get_trace` and `list_traces` to see a detailed log of every message passed between Agent A and Agent B. You can also check which agents exist with `list_agents`. This visibility into agent collaboration makes building autonomous teams predictable.

Setup guide

Set up SketricGen 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 SketricGen tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

The MCP Server exposes its tools directly for your 'crew' to use. Agents treat the available tools—like `get_contact` or `list_workflows`—as methods they can call when their role requires it.

Yes. You run targeted processes using `run_workflow_with_contact`. This allows the entire team's effort to focus only on information relevant to one specific individual or client.

The server handles conversations and contacts. You can list all recent chats with `list_conversations` or pull a single person's details using `get_contact`. This is the core data your agents interact with.

It’s built for it. The architecture supports sequential and hierarchical execution, meaning the team follows a defined process from start to finish without dropping steps or losing context.

Yes. If you need to clear out old records for compliance, `delete_conversation` lets your agent team wipe entire chat threads from the system's history.

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