How to Use the Tactiq MCP in LlamaIndex

Q: How do I use Tactiq and LlamaIndex together for knowledge retrieval?

First, run a query that calls multiple tools like getactionitems and listinsights. Then, index the resulting JSON data into your vector store. When you ask a follow-up question later, LlamaIndex retrieves answers based on those indexed API findings.

Q: Can LlamaIndex handle complex search across recordings?

Yes. By indexing output from searchtranscripts, the system moves past basic keyword matching. It uses semantic understanding to find relevant passages, even if you don't use the exact terminology used in the meeting.

Q: Does LlamaIndex support filtering API access?

Yes. You can use the allowedtools filter during setup. This is great for production environments because it strictly controls which MCP tools are available to build into your final, queryable index.

Q: How do I check basic connectivity with LlamaIndex and Tactiq?

Use the checktactiqstatus tool first. Indexing this simple status result confirms that the underlying API is up before you commit to building a massive, data-intensive knowledge graph.

Build RAG applications with LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Tactiq MCP to LlamaIndex

Create your Vinkius account to connect Tactiq 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 Tactiq with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Index all meeting data semantically.

LlamaIndex turns your raw API results into a searchable knowledge base. Instead of just calling `get_summary`, the output gets indexed alongside documents and configurations in your vector store. This means you can query past sessions using semantic search, getting answers grounded in actual Tactiq API data. You're building RAG applications where the live data from tools like `list_speakers` or `get_meeting` is combined with other source material into one unified index. It’s much smarter than just reading a summary.

Query multiple types of transcripts.

Need to find specific mentions across different recordings? You can combine the data from `list_transcripts` and `search_transcripts`. By indexing both sets, you allow LlamaIndex to answer complex questions that span multiple documents or search criteria. This is powerful because it lets the model query based on meaning, not just keywords. It's a huge leap past simple database lookups.

Build structured data pipelines.

The setup supports filtering allowed tools and including resources (`include_resources=True`). This helps you build highly specific RAG applications where the model knows exactly which MCP tools are available to index. You can limit the scope of your knowledge base effectively. For instance, if you only care about insights, you can configure LlamaIndex to specifically capture and index data from `list_insights` while ignoring other tool outputs.

Setup guide

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

First, run a query that calls multiple tools like `get_action_items` and `list_insights`. Then, index the resulting JSON data into your vector store. When you ask a follow-up question later, LlamaIndex retrieves answers based on those indexed API findings.

Yes. By indexing output from `search_transcripts`, the system moves past basic keyword matching. It uses semantic understanding to find relevant passages, even if you don't use the exact terminology used in the meeting.

It primarily indexes structured outputs from the tools—like speaker lists (`list_speakers`) or detailed action items (`get_action_items`). This allows you to query facts and relationships, not just raw text.

Yes. You can use the `allowed_tools` filter during setup. This is great for production environments because it strictly controls which MCP tools are available to build into your final, queryable index.

Use the `check_tactiq_status` tool first. Indexing this simple status result confirms that the underlying API is up before you commit to building a massive, data-intensive knowledge graph.

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