How to Use the Convai MCP in LangChain

Q: Can LangChain agents use Convai characters?

Yes. Your agents can call getcharacter to pull details and then use getresponse to generate dialogue based on the active persona.

Build complex character reasoning chains in LangChain using Convai tools to manage backstories and narrative triggers.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Convai MCP to LangChain

Create your Vinkius account to connect Convai to LangChain 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 Convai with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Convai character logic in LangChain

Connect `create_character` and `update_character` directly into your LangChain sequences. You can build multi-step reasoning pipelines where the agent decides how to modify personas based on incoming data. Every tool call acts as a link in your chain. You get full visibility into tool inputs and outputs directly through your LangSmith traces.

Manage narrative state with MCP tools

Use `create_narrative_section` and `toggle_narrative` to push state changes through your agents. This lets your code handle complex branching logic without manual intervention. Your agents invoke `list_narrative_sections` to check the current design before deciding the next step. It keeps your narrative flow tight and predictable.

Automate knowledge bank updates

Hook `upload_knowledge_bank` into your data ingestion scripts. When your documents change, your LangChain agents push the latest info to Convai immediately. This ensures your characters stay current without you manually syncing files. Use `delete_knowledge_bank` to clear out stale data during your cleanup cycles.

Setup guide

Set up Convai 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 Convai 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({
    "convai-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 Convai 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 Convai. 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 Convai 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 Convai MCP in LangChain

Install the adapters and initialize the client using the server URL. Pass the tools retrieved from the MCP Server into your agent constructor to start executing.

Yes. Your agents can call `get_character` to pull details and then use `get_response` to generate dialogue based on the active persona.

Vinkius handles the underlying transport security. Your character data, including backstory and knowledge banks, stays encrypted during the transit between the server and your agent.

It does. Because it plugs into LangChain, every interaction is captured in your existing observability stack for debugging.

Convai stores your character definitions and narrative sections on their servers. The MCP connection simply acts as a secure pipe for your agent to read and modify that specific data.

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