How to Use the Capacities MCP in Mastra AI

Q: Can a Mastra AI agent add content to today's note in Capacities?

Yes, the savetodailynote tool is designed for exactly that. Your agent can format a string in Markdown and append it directly to the daily note in a specified space.

Q: How does my Mastra AI workflow know what types of objects exist in Capacities?

Call the getstructures tool. It returns a list of all object definitions, including their names and properties, so your agent can work with any custom type you've defined in your space.

Q: Can Mastra AI agents search for specific content within my Capacities spaces?

Of course. The lookup tool searches across a given space by title or keyword. It's the first step for any workflow that needs to check for existing data before making a change.

Q: What's the difference between getobject and lookup?

lookup is for searching when you don't have an ID, like finding a user by their name. getobject is for fetching a specific item when you already know its unique ID.

Build resilient backend agents that manage your Capacities knowledge base using Mastra AI's workflow engine.

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 Mastra AI

Create your Vinkius account to connect Capacities to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate knowledge graph creation

The `create_object` tool lets your Mastra agent systematically add new items to Capacities. You can build workflows that pull from other data sources—like a CRM or a database—and automatically populate your knowledge graph. Because you're using Mastra, your agent can handle failures. If the `create_object` call fails, the workflow engine can retry it or branch to a different logic path, like logging the error and notifying an admin.

Sync external data with Capacities

Use the `lookup` and `get_object` tools to check if data already exists before you create it. Your agent can search for an item by its title, and if it's not found, use `save_weblink` or `create_object` to add it. This is perfect for building sync jobs with this MCP Server. A workflow could run daily, find new articles from an RSS feed, and use `save_weblink` to add each one to a specific Capacities space, tagging them with `add_tag`.

Build intelligent reporting with Mastra AI

Your agent can inspect the structure of a knowledge base before acting. The `get_space_info` tool gives you a complete picture of a space's object types and their properties. A workflow could use `get_structures` to understand the data model, then use `lookup` to fetch all objects of a certain type. Finally, it could format a report and append it to a specific note using `save_to_daily_note`.

Setup guide

Set up Capacities MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Capacities tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "capacities-mcp-client",
  servers: {
    "capacities-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Capacities Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Capacities tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Capacities transactions"
);
console.log(result.text);

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 Mastra AI

Yes, the `save_to_daily_note` tool is designed for exactly that. Your agent can format a string in Markdown and append it directly to the daily note in a specified space.

Call the `get_structures` tool. It returns a list of all object definitions, including their names and properties, so your agent can work with any custom type you've defined in your space.

Of course. The `lookup` tool searches across a given space by title or keyword. It's the first step for any workflow that needs to check for existing data before making a change.

`lookup` is for searching when you don't have an ID, like finding a user by their name. `get_object` is for fetching a specific item when you already know its unique ID.

The MCP server processes requests for your Capacities objects and notes in an isolated, zero-trust environment. Your Mastra AI agent authenticates with a single Vinkius token, and the connection itself is ephemeral. The server never stores your 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