How to Use the Capacities MCP in LangChain

Q: Can a LangChain agent read my custom schema in Capacities?

Yes, the agent can call getstructures to read your exact workspace definitions. This allows the LangChain agent to discover what properties your custom object types require before it attempts to write new data.

Q: How does LangChain trace tool executions in Capacities?

LangSmith tracks every call to tools like getobject or savemedia automatically. You get complete visibility into the exact payloads, latency, and token costs of your workspace interactions over MCP.

Feed structured Capacities nodes directly into your LangChain reasoning loops with this 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 Capacities MCP to LangChain

Create your Vinkius account to connect Capacities 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 Capacities with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a structured knowledge base with LangChain

The `create_object` tool lets your LangChain agent instantiate strict typed nodes inside your workspace during any step of an active chain. This means a running chain doesn't just output raw text to your terminal; it actively structures its findings into your personal wiki. By coupling this with `add_tag`, your agent groups these new nodes dynamically based on the output of previous chain steps. You can trace this exact creation path inside LangSmith to see how the agent decided to categorize each node using the MCP protocol.

Pull live context into active reasoning chains

The `get_object` tool retrieves the raw graph data of any node inside your workspace for your agent to analyze. Your LangChain agent reads this structured context to ground its decisions, avoiding the hallucinations common with raw LLM prompts. To find the right node first, the agent runs `lookup` across your spaces. Because LangChain supports multi-step ReAct loops, the agent can search for a node, retrieve its contents, and use those properties to format its next API call.

Feed web research directly into daily logs

The `save_weblink` tool writes raw URLs directly into your workspace as structured web objects with automatic preview generation. Your LangChain agent can scrape a source, save the reference, and then link it to an active research task. Using `save_to_daily_note`, the agent appends its progress logs to your daily timeline in clean Markdown format. This turns your daily note into an automated, running log of what your LangChain chains accomplished via this MCP Server.

Setup guide

Set up Capacities 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 Capacities 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({
    "capacities-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 Capacities 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 Capacities. 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 Capacities 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 Capacities MCP in LangChain

You use the langchain-mcp-adapters package to bridge the server. Create a MultiServerMCPClient pointing to your Vinkius endpoint, pull the tools with get_tools, and pass them directly to your agent constructor.

Yes, the agent can call `get_structures` to read your exact workspace definitions. This allows the LangChain agent to discover what properties your custom object types require before it attempts to write new data.

LangSmith tracks every call to tools like `get_object` or `save_media` automatically. You get complete visibility into the exact payloads, latency, and token costs of your workspace interactions over MCP.

The tool returns a clear structural error message. The agent can then run `list_spaces` to find the correct active workspace ID and retry the operation without crashing the entire run.

Your personal notes, graph structures, and media payloads stay isolated within a secure V8 sandbox. Vinkius handles the authorization token securely, meaning your raw API keys never touch the LangChain execution environment directly.

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