2,500+ MCP servers ready to use
Vinkius

Traction Guest MCP Server for OpenAI Agents SDK 24 tools — connect in under 2 minutes

Built by Vinkius GDPR 24 Tools SDK

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

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="Traction Guest Assistant",
            instructions=(
                "You help users interact with Traction Guest. "
                "You have access to 24 tools."
            ),
            mcp_servers=[mcp_server],
        )

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

asyncio.run(main())
Traction Guest
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 Traction Guest MCP Server

Connect your Traction Guest (now Sign In Enterprise) account to any AI agent and take full control of visitor management workflows through natural conversation.

The OpenAI Agents SDK auto-discovers all 24 tools from Traction Guest through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Traction Guest, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

  • Host Management — List, create, and batch-create hosts (employees) who receive and host visitors
  • Location Management — List all office locations and inspect their configuration details
  • Invite Management — Create, read, update, and delete visitor invites for scheduled arrivals
  • Sign-in Tracking — List and manage visitor check-ins, monitor who is currently on-site
  • Group Visits — Create and manage group appointments like tours, training sessions, and interviews
  • Security Watchlists — List and create watchlists for visitor screening
  • Audit Logging — Access audit logs for compliance and security tracking
  • Registration Management — List pre-registered visitors and manage registration queues

The Traction Guest MCP Server exposes 24 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 Traction Guest to OpenAI Agents SDK via MCP

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

01

Install the SDK

Run pip install openai-agents in your Python environment

02

Replace the token

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

03

Run the script

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

04

Explore tools

The agent will automatically discover 24 tools from Traction Guest

Why Use OpenAI Agents SDK with the Traction Guest MCP Server

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

01

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

02

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

03

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

04

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

Traction Guest + OpenAI Agents SDK Use Cases

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

01

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

02

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

03

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

04

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

Traction Guest MCP Tools for OpenAI Agents SDK (24)

These 24 tools become available when you connect Traction Guest to OpenAI Agents SDK via MCP:

01

create_group_visit

Provide group data as JSON including name, scheduled date, expected attendees, host, and location. Example: { "name": "Campus Tour", "scheduledDate": "2026-04-15", "expectedAttendees": 15, "hostId": "host_123", "locationId": "loc_456" } Create a new group visit (group appointment)

02

create_host

Hosts are employees who can receive and host visitors. You must provide host data as JSON including name, email, department, and optionally phone number and location assignment. Example: { "firstName": "John", "lastName": "Doe", "email": "john@company.com", "department": "Engineering" } Create a new host (employee) in Traction Guest

03

create_hosts_batch

Provide an array of host objects as JSON. Each host must include firstName, lastName, and email. This is useful for bulk onboarding new employees or importing host lists from HR systems. Example: [{ "firstName": "John", "lastName": "Doe", "email": "john@company.com" }, { "firstName": "Jane", "lastName": "Smith", "email": "jane@company.com" }] Create multiple hosts in a single batch operation

04

create_invite

You must provide the location_id and invite data as JSON including visitor name, email, host, and scheduled date/time. Example: { "firstName": "Alice", "lastName": "Johnson", "email": "alice@example.com", "hostId": "host_123", "scheduledDate": "2026-04-10", "scheduledTime": "10:00" } Create a new visitor invite for a location

05

create_signin

Provide sign-in data as JSON including visitor information, host, location, and purpose of visit. Example: { "visitorName": "Alice Johnson", "hostId": "host_123", "locationId": "loc_456", "purpose": "Interview" } Create a new visitor sign-in (check-in a visitor on-site)

06

create_watchlist

Provide watchlist data as JSON including name, description, and optionally entries. Example: { "name": "Restricted Visitors", "description": "Individuals not permitted on-site" } Create a new security watchlist

07

delete_group_visit

You must provide the group_visit_id. This action cannot be undone. Use this to cancel scheduled group events that are no longer needed. Delete a group visit

08

delete_invite

You must provide the invite_id. This action cannot be undone. Use this to cancel scheduled visits that are no longer needed. Be careful as this will remove all associated visitor data for that invite. Delete a visitor invite

09

get_group_visit

Use the group_visit_id obtained from list_group_visits to inspect full group visit details. Get detailed information about a specific group visit

10

get_invite

Use the invite_id obtained from list_invites to inspect full invite details. Get detailed information about a specific visitor invite

11

get_location

Use the location_id obtained from list_locations to inspect full location details. This is useful for verifying location configuration before creating invites or managing visitors. Get detailed information about a specific location

12

get_signin

Use the signin_id obtained from list_signins to inspect full visit details. Get detailed information about a specific visitor sign-in

13

list_audit_logs

Use this for compliance reporting, security investigations, and operational auditing. List audit logs for compliance and security tracking

14

list_group_visits

Each group visit includes name, scheduled date, expected attendees, host, and location. Use this to manage tours, training sessions, interviews, and other group events. List all group visits (group appointments) in your organization

15

list_hosts

Each host includes name, email, department, location assignment, and contact information. Use this to see who is available to host visitors and verify host assignments to locations. List all hosts (employees/hosts) in your Traction Guest organization

16

list_invites

Each invite includes visitor name, email, host, scheduled date, location, and status. Use this to see upcoming visitors, manage invite lists, and prepare for expected arrivals. Optionally provide a location_id to filter invites for a specific location. List all visitor invites in your organization

17

list_locations

Each location includes name, address, timezone, and configuration details. Use this to discover available locations before creating invites, sign-ins, or assigning hosts. List all locations in your Traction Guest organization

18

list_packages

Each package includes name, description, included features, and pricing. Use this to understand available visitor management configurations. List packages (visitor management packages/plans) in your organization

19

list_registrations

Each registration includes visitor information, registration date, and associated event or purpose. Use this to manage pre-registration queues and convert registrations to invites. List visitor registrations in your organization

20

list_signins

Each sign-in includes visitor name, host, location, check-in time, check-out time, and purpose of visit. Use this to monitor visitor activity, track who is currently on-site, and review visit history. List all visitor sign-ins (check-ins) in your organization

21

list_watchlists

Watchlists are used to screen visitors against known individuals who should be flagged or denied access. Each watchlist includes name, description, and number of entries. Use this to verify security screening configurations. List all security watchlists in your organization

22

update_group_visit

Common updates include rescheduling, changing expected attendee count, or updating host assignments. You must provide the group_visit_id and the fields to update as JSON. Update an existing group visit

23

update_invite

You must provide the invite_id and the fields to update as JSON. Common updates include rescheduling dates, changing hosts, or updating visitor information. Only provide the fields you want to change. Update an existing visitor invite

24

update_signin

Common updates include recording check-out times, updating visit purpose, or modifying host assignments. You must provide the signin_id and the fields to update as JSON. Update an existing visitor sign-in record

Example Prompts for Traction Guest in OpenAI Agents SDK

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

01

"Show me all upcoming visitor invites for the New York office this week."

02

"Create a group visit for a Campus Tour on April 20th with 20 expected attendees, hosted by Sarah Davis at the Main Office."

03

"Show me who is currently checked in at the New York office and list any security watchlist alerts."

Troubleshooting Traction Guest MCP Server with OpenAI Agents SDK

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

01

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents
02

Agent not calling tools

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

Traction Guest + OpenAI Agents SDK FAQ

Common questions about integrating Traction Guest MCP Server with OpenAI Agents SDK.

01

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.
02

Can I use multiple MCP servers in one agent?

Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
03

Does the SDK support streaming responses?

Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with the Vinkius.

Connect Traction Guest to OpenAI Agents SDK

Get your token, paste the configuration, and start using 24 tools in under 2 minutes. No API key management needed.