Traction Guest MCP Server for LlamaIndex 24 tools — connect in under 2 minutes
LlamaIndex specializes in data-aware AI agents that connect LLMs to structured and unstructured sources. Add Traction Guest as an MCP tool provider through the Vinkius and your agents can query, analyze, and act on live data alongside your existing indexes.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI
async def main():
# Your Vinkius token — get it at cloud.vinkius.com
mcp_client = BasicMCPClient("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
mcp_tool_spec = McpToolSpec(client=mcp_client)
tools = await mcp_tool_spec.to_tool_list_async()
agent = FunctionAgent(
tools=tools,
llm=OpenAI(model="gpt-4o"),
system_prompt=(
"You are an assistant with access to Traction Guest. "
"You have 24 tools available."
),
)
response = await agent.run(
"What tools are available in Traction Guest?"
)
print(response)
asyncio.run(main())
* 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.
LlamaIndex agents combine Traction Guest tool responses with indexed documents for comprehensive, grounded answers. Connect 24 tools through the Vinkius and query live data alongside vector stores and SQL databases in a single turn — ideal for hybrid search, data enrichment, and analytical workflows.
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 LlamaIndex 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 LlamaIndex via MCP
Follow these steps to integrate the Traction Guest MCP Server with LlamaIndex.
Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Run the agent
Save to agent.py and run: python agent.py
Explore tools
The agent discovers 24 tools from Traction Guest
Why Use LlamaIndex with the Traction Guest MCP Server
LlamaIndex provides unique advantages when paired with Traction Guest through the Model Context Protocol.
Data-first architecture: LlamaIndex agents combine Traction Guest tool responses with indexed documents for comprehensive, grounded answers
Query pipeline framework lets you chain Traction Guest tool calls with transformations, filters, and re-rankers in a typed pipeline
Multi-source reasoning: agents can query Traction Guest, a vector store, and a SQL database in a single turn and synthesize results
Observability integrations show exactly what Traction Guest tools were called, what data was returned, and how it influenced the final answer
Traction Guest + LlamaIndex Use Cases
Practical scenarios where LlamaIndex combined with the Traction Guest MCP Server delivers measurable value.
Hybrid search: combine Traction Guest real-time data with embedded document indexes for answers that are both current and comprehensive
Data enrichment: query Traction Guest to augment indexed data with live information before generating user-facing responses
Knowledge base agents: build agents that maintain and update knowledge bases by periodically querying Traction Guest for fresh data
Analytical workflows: chain Traction Guest queries with LlamaIndex's data connectors to build multi-source analytical reports
Traction Guest MCP Tools for LlamaIndex (24)
These 24 tools become available when you connect Traction Guest to LlamaIndex via MCP:
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)
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
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
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
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)
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
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
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
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
get_invite
Use the invite_id obtained from list_invites to inspect full invite details. Get detailed information about a specific visitor invite
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
get_signin
Use the signin_id obtained from list_signins to inspect full visit details. Get detailed information about a specific visitor sign-in
list_audit_logs
Use this for compliance reporting, security investigations, and operational auditing. List audit logs for compliance and security tracking
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
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
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
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
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
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
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
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
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
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
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 LlamaIndex
Ready-to-use prompts you can give your LlamaIndex agent to start working with Traction Guest immediately.
"Show me all upcoming visitor invites for the New York office this week."
"Create a group visit for a Campus Tour on April 20th with 20 expected attendees, hosted by Sarah Davis at the Main Office."
"Show me who is currently checked in at the New York office and list any security watchlist alerts."
Troubleshooting Traction Guest MCP Server with LlamaIndex
Common issues when connecting Traction Guest to LlamaIndex through the Vinkius, and how to resolve them.
BasicMCPClient not found
pip install llama-index-tools-mcpTraction Guest + LlamaIndex FAQ
Common questions about integrating Traction Guest MCP Server with LlamaIndex.
How does LlamaIndex connect to MCP servers?
Can I combine MCP tools with vector stores?
Does LlamaIndex support async MCP calls?
Connect Traction Guest with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Traction Guest to LlamaIndex
Get your token, paste the configuration, and start using 24 tools in under 2 minutes. No API key management needed.