Can the AI add new resources, approve timesheets, or assign projects?

No, this connector is constructed strictly logically explicitly purely as a read-only data extraction protocol naturally seamlessly securely flawlessly organically natively seamlessly explicitly efficiently. It pulls records, reporting scopes organically completely accurately carefully tightly mapped optimally.

What data can the AI retrieve from Runn?

The integration can list projects, people, roles, teams, milestones, and clients. It provides a comprehensive read-only view of your resource planning data.

Can I see project budgets and utilization rates?

Yes. By querying project details, the AI can surface budget allocations, scheduled hours, and utilization metrics for each project in your Runn workspace.

Runn MCP Server for OpenAI Agents SDK 12 tools — connect in under 2 minutes

Name: Runn
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 12 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Runn through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Runn Assistant",
            instructions=(
                "You help users interact with Runn. "
                "You have access to 12 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Runn"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Runn MCP Server

Integrate your conversational AI natively with Runn, the premier real-time resource planning and forecasting platform. This integration enables your assistant to pull essential project metadata, capacity bottlenecks, people configurations, team allocations, and timesheet metrics directly into your sessions.

The OpenAI Agents SDK auto-discovers all 12 tools from Runn through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Runn, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

Analyze Projects & Resources — Extract ongoing engagement details, milestones, and client associations by querying lists natively (list_projects, list_clients). Request detailed readouts of individual operational scopes (get_project).
Audit Roles & Assignments — Find exactly who is assigned to what phase, mapping active allocations accurately (list_assignments, list_phases). Consult team members' details (list_people, get_person) or review globally defined roles (list_roles).
Review Budgets & Actuals — Safely extract reported operational logs (list_actuals) to compare planned work versus billed hours. Account for non-working days naturally via the holidays lists (list_holidays).

The Runn MCP Server exposes 12 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Runn to OpenAI Agents SDK via MCP

Follow these steps to integrate the Runn MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 12 tools from Runn

Why Use OpenAI Agents SDK with the Runn MCP Server

OpenAI Agents SDK provides unique advantages when paired with Runn through the Model Context Protocol.

Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Runn + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Runn MCP Server delivers measurable value.

Automated workflows: build agents that query Runn, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents — one queries Runn, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Runn tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Runn to resolve tickets, look up records, and update statuses without human intervention

Runn MCP Tools for OpenAI Agents SDK (12)

These 12 tools become available when you connect Runn to OpenAI Agents SDK via MCP:

get_person

Retrieves details for a specific person

get_project

Retrieves details for a specific project

list_actuals

Lists actual hours logged (timesheet data)

list_assignments

Lists all resource assignments across projects

list_clients

Lists all clients in the organization

list_holidays

Lists public holidays and non-working days

list_milestones

Lists milestones for a specific project

list_people

Lists all people and resources in Runn

list_phases

Lists project phases for a specific project

list_projects

Lists all projects managed in Runn

list_roles

Lists all defined roles/positions

list_teams

Lists all teams in the workspace

Example Prompts for Runn in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Runn immediately.

"List all active projects mapped."

"Which team is assigned to the Alpha project next week?"

"What are the upcoming milestones for the Beta project?"

Troubleshooting Runn MCP Server with OpenAI Agents SDK

Common issues when connecting Runn to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Runn + OpenAI Agents SDK FAQ

Common questions about integrating Runn MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.