How to Use the Bright Pattern MCP in LlamaIndex

Q: Can I index Bright Pattern call logs into LlamaIndex?

Yes, you can use listinteractions to fetch recent call and chat logs and feed them directly into your index. This turns your raw contact center data into a searchable vector database for RAG applications.

Q: How do I set up the Bright Pattern MCP tool spec in LlamaIndex?

Initialize the BasicMCPClient with your Vinkius URL, then wrap it in McpToolSpec. Pass the resulting tools list to your FunctionAgent to let your agent query the contact center.

Q: Does LlamaIndex support filtering tools from this Bright Pattern MCP server?

Yes, you can use the allowedtools filter to only expose specific tools like getrealtimestats. This keeps your agent focused on performance metrics while ignoring user management tools.

Index live contact center records into LlamaIndex to build a searchable knowledge base.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bright Pattern MCP to LlamaIndex

Create your Vinkius account to connect Bright Pattern to LlamaIndex 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 Bright Pattern with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Agent Skills for RAG

`list_skills` retrieves the current skill configurations for agent profiles in your contact center. LlamaIndex takes this raw output and indexes it into a vector store, allowing your agent to run semantic searches over who can handle specific technical issues. You stop guessing who is qualified and start querying your workforce data. By combining this with `list_users`, your index links names to specific technical capabilities. When a complex issue arises, the system queries this index to instantly find the best available expert.

Query Interaction History using this MCP Server

`list_interactions` retrieves raw call and chat records to build a dynamic, searchable index of customer touchpoints. LlamaIndex stores these records, letting your agent search past conversations for resolved issues or recurring complaints. You turn a flat list of calls into a searchable knowledge base. Your agent uses `get_interaction_details` to fetch deep metadata on specific flagged sessions. This detailed data updates your index in real time, ensuring your RAG queries always return current information.

Map Tenant Configurations Instantly

`get_tenant_config` pulls the core settings of your contact center environment directly into your RAG pipeline. LlamaIndex parses this configuration, giving your agent a clear map of your dialing rules, routing logic, and system limits through this MCP server. It eliminates manual reference checks when troubleshooting system behavior. When combined with `list_services`, the index creates a structured view of how your contact center is structured. Your agent queries this index to find configuration bottlenecks without reading through database tables.

Setup guide

Set up Bright Pattern MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Bright Pattern MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Bright Pattern tools.",
)
response = await agent.run("List recent Bright Pattern data")

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 Bright Pattern. 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 Bright Pattern 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 Bright Pattern MCP in LlamaIndex

Yes, you can use `list_interactions` to fetch recent call and chat logs and feed them directly into your index. This turns your raw contact center data into a searchable vector database for RAG applications.

Initialize the `BasicMCPClient` with your Vinkius URL, then wrap it in `McpToolSpec`. Pass the resulting tools list to your `FunctionAgent` to let your agent query the contact center.

Yes, you can use the `allowed_tools` filter to only expose specific tools like `get_realtime_stats`. This keeps your agent focused on performance metrics while ignoring user management tools.

LlamaIndex grounds its answers in the live data fetched by tools like `get_realtime_stats`. The agent reads current queue numbers directly from the API, preventing it from making up statistics.

Your tenant configuration and agent team lists pass through an ephemeral V8 sandbox that destroys the MCP session data immediately after execution. No customer records or configuration profiles are ever cached on Vinkius servers.

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