How to Use the Capacities MCP in CrewAI

Q: How can a CrewAI agent get a list of all my spaces in Capacities?

Give your agent the listspaces tool. It returns a simple list of all spaces in your account. Another agent in the crew can then use that list to decide where to perform its tasks.

Q: How can my CrewAI team understand the data schema of my Capacities account?

Have an 'Analyst' agent use the getspaceinfo and getstructures tools. This gives your crew complete knowledge of all available object types and their properties, allowing them to work with your custom data structures.

Q: Is it possible to attach files using this MCP Server?

Yes, the savemedia tool is for attaching media payloads to existing records in Capacities. Your agent needs to locate the media and provide its data to the tool along with the ID of the record to attach it to.

Deploy autonomous crews of AI agents to research, organize, and build your Capacities knowledge base with CrewAI.

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 CrewAI

Create your Vinkius account to connect Capacities to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create an autonomous research crew

Assign one agent the role of 'Researcher.' This agent's job is to use external tools to find information online, then use the `save_weblink` tool to store interesting URLs in Capacities. A second 'Archivist' agent can then follow up. It uses `get_object` to read the saved weblinks and then `add_tag` to categorize them. Your crew builds an organized, searchable library without any human input.

Automate daily briefings for your team

A 'Reporter' agent can be tasked to run every morning. It uses `lookup` to find all items tagged 'priority' or created in the last 24 hours inside your shared Capacities space. After gathering the data, the agent formats a summary in Markdown and uses `save_to_daily_note` to append it to that day's note. Your whole team gets a briefing waiting for them, generated automatically by your CrewAI agent.

Maintain your knowledge base with a CrewAI team

Design a 'Janitor' agent that periodically scans your space using this MCP Server. It can use `get_structures` to understand the valid object types you've defined and look for content that doesn't match. If it finds malformed or untagged data, it can either try to fix it with `add_tag` or create a new task object using `create_object`. That new task object can be assigned to a human for review.

Setup guide

Set up Capacities MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Capacities tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Capacities Analyst",
    goal="Access and analyze Capacities data via MCP.",
    backstory="Expert analyst with direct Capacities access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Capacities transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Capacities Analyst",
        goal="Access and analyze Capacities data via MCP.",
        backstory="Expert analyst with direct Capacities access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Capacities transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Give your agent the `list_spaces` tool. It returns a simple list of all spaces in your account. Another agent in the crew can then use that list to decide where to perform its tasks.

Yes, this is a core pattern for multi-agent systems. An agent can use `create_object` to generate a new item. It can then pass the ID of that new object to another agent in the crew for analysis or processing.

Have an 'Analyst' agent use the `get_space_info` and `get_structures` tools. This gives your crew complete knowledge of all available object types and their properties, allowing them to work with your custom data structures.

Yes, the `save_media` tool is for attaching media payloads to existing records in Capacities. Your agent needs to locate the media and provide its data to the tool along with the ID of the record to attach it to.

Your agents interact with your Capacities weblinks, notes, and objects through this server, which runs in a secure, sandboxed Vinkius environment. Authentication is handled via a single token, not your direct credentials. Each transaction is isolated and stateless.

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