How to Use the Tactiq MCP in LangChain

Q: How do I use Tactiq and LangChain together for research?

Run listmeetings first to map out the available data. Then, pass a specific meeting ID into both gettranscript and listinsights. Your agent can process these two outputs in sequence—the transcript provides raw text, and the insights provide structured analysis.

Q: What happens when I use Tactiq and LangChain to get action items?

Your agent runs getactionitems which pulls the task list directly. If those tasks are incomplete, it can then call listspeakers to see who was assigned what, giving you immediate context on accountability.

Build multi-step reasoning pipelines with LangChain.

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 LangChain

Create your Vinkius account to connect Tactiq to LangChain — 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Chain Meetings and Actions together.

You can build complex workflows where the output of one call feeds directly into another. For instance, your agent first runs `list_meetings` to find relevant sessions, then uses that data to pass IDs to `get_summary`. This chaining process allows you to move beyond simple lookups and create true multi-step reasoning pipelines. Because LangChain supports this kind of ordered execution, it lets you design agents that decide exactly which MCP tool to call and in what sequence. You're not just calling tools; you're building an automated decision engine.

Search transcripts across multiple calls.

Need to check historical context? Your agent can first use `list_transcripts` to gather all available identifiers. Then, it passes those IDs into `search_transcripts`, letting the LangChain client perform a targeted search across every recording. This means you pull together data from multiple sources in one logical flow. This multi-step approach is key for complex research tasks. Instead of writing separate code blocks for searching and summarizing, your agent executes them sequentially—the result set becomes the input for the next step.

Validate connectivity with simple calls.

Before building anything big, you need to know if the connection works. The `check_tactiq_status` tool lets your agent verify the API connectivity instantly. This quick check confirms that everything is online and ready for use. It’s a reliable first step in any LangChain pipeline. You can make this call early in your chain to ensure data integrity before attempting more complex, time-consuming tasks like fetching insights or action items.

Setup guide

Set up Tactiq MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Tactiq tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "tactiq-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Tactiq transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Run `list_meetings` first to map out the available data. Then, pass a specific meeting ID into both `get_transcript` and `list_insights`. Your agent can process these two outputs in sequence—the transcript provides raw text, and the insights provide structured analysis.

Yep. The client supports multi-server aggregation. This is huge if you're not just using Tactiq, but combining it with other MCP tools in one chain. You can manage multiple data sources from a single agent run.

Your agent runs `get_action_items` which pulls the task list directly. If those tasks are incomplete, it can then call `list_speakers` to see who was assigned what, giving you immediate context on accountability.

Absolutely. The framework provides full observability via tracing. You can see the latency and token usage for every tool call—like `get_summary` or `search_transcripts`—which is critical when building complex, production-grade chains.

Yes. While stateless by default, you can use the client's session method (`client.session()`) to maintain persistent context throughout your multi-step workflows. This means intermediate results aren't lost between tool calls.

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