How to Use the Forecast MCP in OpenAI Agents SDK

Q: How do I connect Forecast to the OpenAI Agents SDK?

Install openai-agents via pip. Create an MCPServerStreamableHttp instance with your endpoint URL. Pass it into the mcpservers array when you initialize your Agent to expose this MCP Server.

Q: Can the OpenAI Agents SDK cache Forecast tool definitions?

Yes. Set cacheToolsList=True in your server parameters. The agent stores the schemas for listtasks and listprojects locally to speed up execution times.

Q: Does Forecast work with OpenAI Agents SDK handoffs?

It works exactly as expected. A researcher agent can query listmilestones, summarize the deadlines, and hand that context over to a separate reporting agent.

Connect the Forecast MCP Server to the OpenAI Agents SDK to manage project resources and tasks with built-in guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect Forecast to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Forecast Project Data in OpenAI Agents SDK

Your agent pulls live project timelines directly from Forecast using `get_project` and `list_projects`. You define the safety constraints in your OpenAI Agent constructor. If an autonomous agent tries to pull data outside its scope, the built-in guardrails block the execution before it hits the API. Handoffs work perfectly here. One specialized agent checks team availability via `list_people`, then passes the context to a scheduling agent. You track every single API call and agent decision through the OpenAI tracing dashboard.

Monitor Milestones and Deadlines

The `list_milestones` tool feeds project deadlines straight into your Python application. Your deployed product reads these dates and aligns them against current task statuses from `list_tasks`. Auto-discovery means you just pass the MCP Server object to your agent, and it knows exactly how to query the data. Production systems need caching to avoid rate limits. Set `cacheToolsList=True` in your setup. This forces the agent to remember the tool schemas, reducing latency when checking task progress across hundreds of active projects.

Query Client Portfolios

Use `list_clients` to pull your entire customer directory into the agent's context window. The agent groups active accounts and matches them against ongoing work. It reads the raw JSON response and formats it according to your strict output instructions. You do not need to write custom HTTP clients or parsing logic. The OpenAI Agents SDK handles the network transport layer. You just initialize the `MCPServerStreamableHttp` connection and let the agent manage the data fetching.

Setup guide

Set up Forecast MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Forecast tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Forecast tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Forecast tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Forecast Agent",
            instructions="You have access to Forecast tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents` via pip. Create an `MCPServerStreamableHttp` instance with your endpoint URL. Pass it into the `mcp_servers` array when you initialize your Agent to expose this MCP Server.

Yes. Set `cacheToolsList=True` in your server parameters. The agent stores the schemas for `list_tasks` and `list_projects` locally to speed up execution times.

It works exactly as expected. A researcher agent can query `list_milestones`, summarize the deadlines, and hand that context over to a separate reporting agent.

Check your OpenAI tracing dashboard. Every call to this MCP Server gets logged there, showing the exact payloads sent to Forecast and the raw responses returned.

The server reads task descriptions, team availability, and project timelines. Vinkius runs this connection inside a V8 Isolate Sandbox. The environment destroys itself the moment your script finishes execution, leaving zero persistent state.

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