How to Use the Tome (AI Storytelling) MCP in LangChain

Q: Does Tome (AI Storytelling) support listing multiple tomes at once?

Yes. The listtomes function lets your agent retrieve a list of all existing presentations within the currently targeted workspace, giving you a full overview.

Build multi-step narrative pipelines with LangChain and the Tome (AI Storytelling) MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Tome (AI Storytelling) MCP to LangChain

Create your Vinkius account to connect Tome (AI Storytelling) 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 Tome (AI Storytelling) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chaining Multi-Step Story Generation

Your agent can build entire presentations by connecting tool calls. For instance, you can first use `list_workspaces` to find a target project, then pass that workspace ID into `get_tome`. The final step could be calling `add_page` with the retrieved content structure. This sequential approach makes sure your reasoning is solid. You're not just running random tools; you're building a reliable chain where one tool's output directly dictates the next action.

Managing and Creating Tomes via MCP Server

Need to scaffold a presentation from scratch? The `create_tome` function handles that setup instantly. You can then immediately follow up by using `list_tomes` to verify the new entry appeared in your workspace list. This pattern lets you programmatically manage the lifecycle of any presentation, whether it's for a client pitch or an internal report. It keeps all your story generation steps contained and traceable.

Retrieving Specific Content Pages

Don't want to download the whole thing just to check one slide? Use `get_tome` to pull detailed metadata on a specific presentation. If you know the exact pages, `list_tomes` gives you enough context to pinpoint exactly what you need. This precise control means your agent only pulls relevant data points, saving time and tokens when building complex decision trees.

Setup guide

Set up Tome (AI Storytelling) 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 Tome (AI Storytelling) 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({
    "tome-ai-storytelling-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 Tome (AI Storytelling) 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 Tome. 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 Tome (AI Storytelling) 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 Tome (AI Storytelling) MCP in LangChain

You incorporate the MCP Server tools directly into your agent's tool list. Your agent decides when to call `list_tomes` or `add_page` based on the prompt context, allowing for complex workflows.

This MCP Server manages metadata about your workspaces and tomes. The specific data type it handles is 'workspace ID' and 'tome name/ID', which are used for context passing between tools.

Absolutely. Since the MCP Server exposes every function as a callable tool, you can integrate it into multi-step reasoning pipelines alongside database lookups or API calls.

Yes. The `list_tomes` function lets your agent retrieve a list of all existing presentations within the currently targeted workspace, giving you a full overview.

You initialize the MultiServerMCPClient and pass the server endpoint. From there, your agent's orchestration layer handles the rest, making sure every tool call is logged for observability.

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