How to Use the Forecast MCP in Pydantic AI

Q: How do I integrate Forecast with Pydantic AI?

Install pydantic-ai-slimmcp. Define your connection using MCPToolset with your HTTP endpoint and pass it to the toolsets array in your Agent setup.

Q: Which MCP transport should I use for the Forecast MCP Server in Pydantic AI?

Use the unified MCPToolset with an HTTP URL. The older MCPServerHTTP class is deprecated in current versions of the framework.

Connect the Forecast MCP Server to Pydantic AI to enforce strict type validation on all project tasks and team milestones.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Forecast MCP to Pydantic AI

Create your Vinkius account to connect Forecast 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 Forecast with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Forecast Projects via MCP Server

The `get_project` and `list_projects` tools return data that Pydantic AI validates at runtime against your custom models. If the API changes or returns a missing field, the framework throws a loud validation error. You never deal with silent corruption or hallucinated project dates. Use the `MCPToolset` class to bind the endpoint. You pass the unified toolset to your Agent constructor. The framework translates the JSON responses into native Python objects before your code ever touches them.

Enforce Task Data Integrity

Agents query `list_tasks` and `list_milestones` to build production schedules. Pydantic AI ensures every deadline and task ID matches the exact schema you defined. The user cares about correctness, and this setup guarantees the data matches your expectations. This approach is completely model-agnostic. You can swap between Anthropic, OpenAI, or local models without rewriting your Forecast integration. The framework handles the tool execution and validation regardless of the underlying LLM.

Map Clients and Team Members

Execute `list_clients` to fetch your customer roster and `list_people` to check staff availability. Pydantic AI parses the nested JSON objects into strict data classes. Your downstream Python code gets guaranteed structures instead of raw dictionaries. Install the slim package with MCP support to keep your dependencies light. The framework supports Streamable HTTP out of the box. You just point it at the external URL and let the validation engine do the heavy lifting.

Setup guide

Set up Forecast 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": {
        "forecast-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Forecast 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 Forecast. 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 Forecast 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 Forecast MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]`. Define your connection using `MCPToolset` with your HTTP endpoint and pass it to the `toolsets` array in your Agent setup.

The framework immediately throws a validation error. Your agent stops execution rather than passing malformed task data into your application logic.

Yes. The framework is model-agnostic. As long as your local model supports function calling, it can query `list_projects` and parse the results.

Use the unified `MCPToolset` with an HTTP URL. The older `MCPServerHTTP` class is deprecated in current versions of the framework.

The integration touches project timelines, staff names, and client details. We route all traffic through isolated sandboxes that spin down immediately after the HTTP response. No external databases store your operational logs.

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