How to Use the GPTBots MCP in CrewAI

Q: How do I add GPTBots tools to a CrewAI agent?

Add the server URL directly to the agent's mcps list during initialization. For more control, import MCPServerHTTP from crewai.mcp and use a tool filter to expose only the specific tools your agent needs.

Q: Can a CrewAI agent trigger external workflows on GPTBots?

Yes, an agent can use triggerworkflow to start background tasks on the remote platform. The agent then passes the workflow ID to another crew member, who uses queryworkflow to monitor progress.

Q: How do CrewAI members share GPTBots knowledge base data?

One agent can search the index using listknowledgedocuments and share the document list with the crew. If context is missing, another agent can call createknowledgedocument to upload the required text.

Q: How does the GPTBots server protect our customer conversation logs?

Access to conversation logs via getconversation is restricted by workspace tokens managed securely on the Vinkius platform. This ensures that your CrewAI agents only get chat history belonging to your authorized accounts.

Run teams of specialized agents that manage GPTBots databases and documents 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 GPTBots MCP to CrewAI

Create your Vinkius account to connect GPTBots 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 GPTBots with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate multi-agent document ingestion pipelines

`create_knowledge_document` allows a specialized writer agent to upload research findings directly to your knowledge base. Meanwhile, a researcher agent can use `list_knowledge_documents` to check which files are already indexed. This division of labor prevents duplicate uploads and keeps your knowledge base clean. The crew coordinates these tasks using shared memory, ensuring that no agent acts on stale file directories.

Manage automated workflows using CrewAI and MCP Server tools

`trigger_workflow` initiates complex background tasks that your crew needs to track over time. Instead of blocking execution, a supervisor agent can delegate the tracking task to a subordinate using our MCP Server. That subordinate agent uses `query_workflow` to check the status at regular intervals. Once the background process finishes, the agent reports back to the crew so they can begin analyzing the output.

Inspect chat history for quality assurance

`list_conversations` lets a moderator agent scan active chat threads for customer issues. If the moderator flags a problematic session, it gets the full transcript using `get_conversation` to diagnose the issue. The moderator can then use `send_bot_message` to inject corrective instructions or take over the conversation. This multi-agent feedback loop ensures your production agents maintain high response standards.

Setup guide

Set up GPTBots 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 GPTBots tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Add the server URL directly to the agent's `mcps` list during initialization. For more control, import `MCPServerHTTP` from `crewai.mcp` and use a tool filter to expose only the specific tools your agent needs.

Yes, an agent can use `trigger_workflow` to start background tasks on the remote platform. The agent then passes the workflow ID to another crew member, who uses `query_workflow` to monitor progress.

One agent can search the index using `list_knowledge_documents` and share the document list with the crew. If context is missing, another agent can call `create_knowledge_document` to upload the required text.

The integration supports stdio, SSE, and HTTP transports. For most multi-agent setups, configuring HTTP via Vinkius is the easiest way to keep your crew connected across different environments using the MCP standard.

Access to conversation logs via `get_conversation` is restricted by workspace tokens managed securely on the Vinkius platform. This ensures that your CrewAI agents only get chat history belonging to your authorized accounts.

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