How to Use the Ably MCP in CrewAI

Q: Can I restrict which Ably tools my CrewAI agents can use?

Yes. Use MCPServerHTTP from crewai.mcp and apply a toolfilter. This lets you give one agent read-only access while another gets permission to publish.

Equip your CrewAI teams with real-time communication tools. Connect this MCP Server to let specialized agents monitor channels autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ably MCP to CrewAI

Create your Vinkius account to connect Ably 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 Ably with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assign monitor agents to Ably channels

A dedicated researcher agent runs `get_messages` to constantly watch specific channels for keywords or anomalies. Because CrewAI shares memory across the team, this agent instantly passes relevant findings to a moderator agent for review. The same monitor tracks overall system health. By calling `get_stats`, the agent evaluates usage spikes and hands a summary to the manager agent to decide if scaling is necessary.

Autonomous moderation via CrewAI MCP Server

When the team detects a policy violation, the action agent fires `update_message` to delete or append a warning to the offending chat. This happens entirely without human intervention, keeping your channels clean around the clock. If the user continues to spam, the escalation agent executes `revoke_tokens`. This immediately boots the bad actor from the system by invalidating their API access before their session naturally expires.

Coordinate multi-channel broadcasts

A communications agent uses `batch_push_publish` to send targeted mobile alerts after analyzing an ongoing incident. The hierarchical execution ensures the manager agent approves the text before the broadcast goes out. To see who received the alert, a follow-up agent triggers `get_presence`. It maps out which users are currently active and logs the audience size for the final task report.

Setup guide

Set up Ably 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 Ably tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Ably 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="Ably Analyst",
        goal="Access and analyze Ably data via MCP.",
        backstory="Expert analyst with direct Ably access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Ably 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 Ably. 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 Ably 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 Ably MCP in CrewAI

Pass your Vinkius endpoint directly into the mcps array when defining the agent. CrewAI handles the HTTP transport and exposes the messaging tools automatically.

Yes. Use MCPServerHTTP from crewai.mcp and apply a tool_filter. This lets you give one agent read-only access while another gets permission to publish.

One agent fetches the active member list and stores it in the shared memory. Other agents in the crew then read that context to make decisions about who to notify.

If you use hierarchical execution, the manager evaluates the proposed push payload. It only allows the worker agent to execute the publish tool if the text meets your criteria.

Vinkius processes your message payloads and presence history inside an ephemeral, isolated container. The sandbox executes the tool call for your crew and terminates instantly. Nobody stores or inspects your raw communication 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