How to Use the Outseta MCP in LlamaIndex

Q: How do I load Outseta data into LlamaIndex vector stores using the MCP Server?

Install llama-index-tools-mcp and initialize the basic client with your Vinkius URL. Convert the tools using McpToolSpec and pass them to your search index pipeline.

Q: Can LlamaIndex query Outseta subscriptions during a search?

Yes. Your agent runs listsubscriptions to pull live data, indexes it on the fly, and uses it to ground its response.

Q: Does LlamaIndex support filtering Outseta MCP tools?

Yes. You can use the allowedtools filter to restrict your agent to safe tools like getuserprofile while blocking write tools.

Q: How do I combine Outseta CRM data with local PDFs in LlamaIndex?

Use listpeople to pull contact records, index them alongside your PDFs into a single vector store, and query them together.

Index your Outseta CRM, billing data, and support tickets into LlamaIndex vector stores for semantic search.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Outseta MCP to LlamaIndex

Create your Vinkius account to connect Outseta to LlamaIndex — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Outseta with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Semantic search over Outseta support tickets in LlamaIndex

The `list_tickets` tool retrieves customer support conversations directly into your LlamaIndex pipelines. Your agent indexes these support threads into a vector store, making past customer issues searchable. When a new support request comes in, the agent queries the vector index of past tickets to find similar resolutions. This setup stops your team from answering the same questions twice by surfacing historical fixes instantly.

Context-rich RAG using CRM data

The `get_person` tool fetches detailed contact records to ground your LlamaIndex generation in real user history. Your agent pulls the person's profile and indexes it alongside local documents to answer account-specific questions. This MCP Server integration ensures your RAG applications do not hallucinate user details. By combining `list_activities` with your indexed files, the agent explains account usage patterns using actual CRM data.

Indexing Outseta billing plans and invoices

The `list_plans` tool extracts pricing tiers so your LlamaIndex agent can parse and index your entire catalog. The agent matches user queries about pricing against the actual active plans in your database. By indexing outputs from `list_invoices`, your search index answers complex billing questions. Your agent checks the indexed invoice history to explain charges to customers without manual lookups.

Setup guide

Set up Outseta 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 Outseta 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 Outseta tools.",
)
response = await agent.run("List recent Outseta 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 Outseta. 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 Outseta 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 Outseta MCP in LlamaIndex

Install `llama-index-tools-mcp` and initialize the basic client with your Vinkius URL. Convert the tools using `McpToolSpec` and pass them to your search index pipeline.

Yes. Your agent runs `list_subscriptions` to pull live data, indexes it on the fly, and uses it to ground its response.

Yes. You can use the `allowed_tools` filter to restrict your agent to safe tools like `get_user_profile` while blocking write tools.

Use `list_people` to pull contact records, index them alongside your PDFs into a single vector store, and query them together.

Yes. The MCP Server runs in a zero-trust, ephemeral sandbox on Vinkius. Your CRM data and customer invoices are only processed in memory during the tool execution and are never cached.

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