How to Use the Jibble MCP in Pydantic AI

Q: How do I integrate the Jibble MCP toolset with Pydantic AI?

Install pydantic-ai-slimmcp and initialize your tools using the unified MCPToolset class pointing to your Vinkius HTTP URL. Pass this toolset directly into the Agent constructor to expose all ten endpoints.

Q: Does Jibble tool execution in Pydantic AI support runtime validation?

Absolutely. Every JSON payload returned by tools like listactivities is validated against Pydantic schemas before the agent can use the data, protecting your application from unexpected API changes.

Q: How does this MCP Server protect sensitive Jibble project data?

Your project details from listprojects and activity logs from listtimeentries are processed within zero-trust ephemeral sandboxes. Vinkius never retains your API tokens or tracking payloads, ensuring complete data isolation.

Build type-safe Pydantic AI agents that query Jibble time entries and projects with strict runtime schema validation.

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 Pydantic AI

Create your Vinkius account to connect Jibble to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Jibble time logs with Pydantic AI

If your payroll system expects strict decimal hours and gets a malformed string, everything breaks. By calling `get_time_entry` through this MCP Server, the framework instantly validates the returned payload against your defined Pydantic models. Any schema mismatch or missing field triggers an immediate, loud validation error at runtime. This prevents corrupt data from silently polluting your downstream payroll databases or invoicing pipelines.

Enforce strict schemas on client project lists

Pulling metadata like `list_projects` or `list_clients` can often return inconsistent structures if different managers created them. The agent forces these responses into clean, typed structures, guaranteeing that every project ID matches your expected format. This strict typing makes it incredibly easy to map hours to specific client accounts. Your agent can confidently process billing summaries, knowing that the structural integrity of the data is guaranteed before execution.

Audit workforce rosters without structural drift

Personnel directories change constantly as people join or leave departments. By routing your queries through this MCP Server, querying `list_people` allows your agent to pull active rosters and validate fields like emails and internal IDs against strict corporate schemas. The model-agnostic nature of the framework means you can run these audits using any LLM provider. You get identical, type-safe validation whether you are using OpenAI, Anthropic, or a local model to parse your workforce groups.

Setup guide

Set up Jibble MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "jibble-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Jibble tools.",
)

result = await agent.run("List recent Jibble transactions")
print(result.output)

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 Pydantic AI

Install `pydantic-ai-slim[mcp]` and initialize your tools using the unified `MCPToolset` class pointing to your Vinkius HTTP URL. Pass this toolset directly into the `Agent` constructor to expose all ten endpoints.

Absolutely. Every JSON payload returned by tools like `list_activities` is validated against Pydantic schemas before the agent can use the data, protecting your application from unexpected API changes.

The framework will raise a validation error immediately instead of letting the agent hallucinate missing fields. This fail-fast design ensures your time-tracking automation remains completely reliable.

The setup supports both Streamable HTTP and SSE transports, provided your server runs externally. This allows you to choose the best networking model for your production infrastructure.

Your project details from `list_projects` and activity logs from `list_time_entries` are processed within zero-trust ephemeral sandboxes. Vinkius never retains your API tokens or tracking payloads, ensuring complete data isolation.

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