How to Use the Jibble MCP in AutoGen

Q: How do I add Jibble MCP tools to an AutoGen agent?

Install autogen-extmcp and use mcpservertools to feed Jibble data directly to your agents. Pass the resulting tools list to your AssistantAgent constructor to expose tools like listtimeentries.

Q: How does AutoGen handle Jibble MCP API schemas?

The McpToolAdapter handles schema conversion automatically. It maps the Jibble API JSON schemas for tools like getperson into the format AutoGen agents expect for conversation planning.

Q: Where are my Jibble employee details processed?

All Jibble data, including names and emails from listpeople, is processed inside Vinkius's zero-trust V8 sandbox. Your API tokens are encrypted, and data is never cached or stored after the session ends.

Run multi-agent AutoGen debates using this MCP Server to cross-reference Jibble time logs, projects, and locations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Jibble MCP to AutoGen

Create your Vinkius account to connect Jibble to AutoGen 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 Jibble with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent Jibble payroll audits

Let specialized agents debate your billing accuracy. You can set up one AutoGen agent to pull active hours using `list_time_entries` while a second agent checks project budgets with `list_projects`, allowing them to negotiate and flag discrepancies. This collaborative approach surfaces anomalies that single-agent systems miss. The agents discuss the findings in a structured conversation, using `get_time_entry` to verify suspicious logs before finalizing the report.

Collaborative team coordination

Manage workforce distribution through automated agent discussions. One agent can monitor team structures using `list_groups` while another checks physical site presence via `list_locations` to ensure key projects are fully staffed. When a gap is found, the agents coordinate to suggest reassignments, pulling individual profiles with `get_person` to verify skills and availability before presenting options to you.

Compliance checks with AutoGen and MCP

Ensure your team only clocks in from authorized locations. An audit agent can fetch active coordinates using `get_time_entry` and debate compliance with a policy agent that holds rules for specific clients from `list_clients`. This setup stops manual compliance reviews from eating your afternoon. The agents use this MCP Server to verify that physical locations match contract requirements, generating a consensus-based report on your operational status.

Setup guide

Set up Jibble MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Jibble tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Jibble_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Jibble data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Jibble_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Jibble data")
    print(result.messages[-1].content)

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 Jibble. 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 Jibble 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 Jibble MCP in AutoGen

Install `autogen-ext[mcp]` and use `mcp_server_tools` to feed Jibble data directly to your agents. Pass the resulting tools list to your `AssistantAgent` constructor to expose tools like `list_time_entries`.

Yes, you can share the same Jibble tools list across multiple agents. For example, your billing agent can call `list_clients` while your operations agent calls `list_projects` to coordinate their tasks.

The `McpToolAdapter` handles schema conversion automatically. It maps the Jibble API JSON schemas for tools like `get_person` into the format AutoGen agents expect for conversation planning.

Yes, you can connect using the Streamable HTTP transport parameters in AutoGen. This allows your multi-agent system to interact with your Jibble workspace securely over the web.

All Jibble data, including names and emails from `list_people`, is processed inside Vinkius's zero-trust V8 sandbox. Your API tokens are encrypted, and data is never cached or stored after the session ends.

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