How to Use the Convai MCP in CrewAI

Q: Can I restrict which Convai tools my CrewAI agents can access?

Yes, you can use CrewAI's toolfilter configuration. This lets you restrict sensitive tools like deletecharacter to your admin agent, while leaving conversational tools open to your writer agents.

Q: How does CrewAI protect my audio streams and live chat session transcripts?

Every interaction with connectlive or getchatsessiondetails is secured via Vinkius's zero-trust architecture. Your raw audio and chat logs are processed in ephemeral V8 isolates, meaning your players' conversation history is never stored or exposed.

Deploy cooperative agent teams to design, evaluate, and update your game characters autonomously using CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Convai MCP to CrewAI

Create your Vinkius account to connect Convai 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 Convai with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build multi-agent NPC writing crews with CrewAI

This server uses `generate_backstory`, `list_voices`, and `create_character` to let specialized agent crews design and deploy game characters. This MCP setup ensures your game characters have deep, consistent backstories. The agents share memory and pass data sequentially, turning a raw prompt into a fully functional game character.

Run autonomous quality assurance via this MCP Server

This server calls `list_chat_sessions`, `get_chat_session_details`, and `evaluate_conversation` to let an autonomous crew monitor and grade dialogue quality. If the dialogue score falls below your threshold, a writer agent automatically uses edit_narrative_section to fix the NPC's conversational flow. Your game's narrative quality improves autonomously without your developers lifting a finger.

Keep game knowledge bases updated autonomously

This server exposes `list_knowledge_bank`, `upload_knowledge_bank`, and `delete_knowledge_bank` to let librarian agents manage game reference materials over this MCP connection. When updates are found, the librarian agent uses upload_knowledge_bank and delete_knowledge_bank to refresh the character's memory. This keeps your NPCs perfectly aligned with the latest state of your game world.

Setup guide

Set up Convai 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 Convai tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass your Vinkius URL directly into your agent's mcps list during initialization. For more control, use MCPServerHTTP and apply a tool_filter to only give specific agents access to tools like create_character.

Yes, you can set up a sequential crew where one agent uses get_response to chat with a character, and a second agent uses evaluate_conversation to analyze the response quality.

Your narrative designer agent can monitor chat logs and autonomously call create_narrative_trigger when a player reaches a specific milestone. This lets your agents build interactive quests on the fly.

Yes, you can use CrewAI's tool_filter configuration. This lets you restrict sensitive tools like delete_character to your admin agent, while leaving conversational tools open to your writer agents.

Every interaction with connect_live or get_chat_session_details is secured via Vinkius's zero-trust architecture. Your raw audio and chat logs are processed in ephemeral V8 isolates, meaning your players' conversation history is never stored or exposed.

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