4,000+ servers built on vurb.ts
Vinkius
Mastra AISDK
Mastra AI
Ably MCP Server

Bring Pub Sub
to Mastra AI

Learn how to connect Ably to Mastra AI and start using 14 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.

MCP Inspector GDPR Free for Subscribers
Batch PresenceBatch PublishBatch Push PublishGet Channel MetadataGet MessageGet MessagesGet PresenceGet Presence HistoryGet StatsList ChannelsPublish MessagePush PublishRevoke TokensUpdate Message

Compatible with every major AI agent and IDE

ClaudeClaude
ChatGPTChatGPT
CursorCursor
GeminiGemini
WindsurfWindsurf
VS CodeVS Code
JetBrainsJetBrains
VercelVercel
+ other MCP clients
Ably

What is the Ably MCP Server?

Connect your Ably account to any AI agent to orchestrate real-time communication infrastructure through natural language. This server provides full access to the Ably REST API for robust pub/sub messaging and presence management.

What you can do

  • Messaging — Publish messages to single or multiple channels, retrieve message history, and update or delete existing messages.
  • Presence Tracking — Monitor real-time member status and history within specific channels to see who is online.
  • Push Notifications — Send direct push notifications to devices or client IDs for mobile and web engagement.
  • Channel Management — List active channels, fetch metadata, and monitor usage statistics across your application.
  • Security & Tokens — Revoke tokens before expiry to maintain tight control over your real-time infrastructure access.

How it works

  1. Subscribe to this server
  2. Enter your Ably API Key
  3. Start managing your real-time streams from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • Backend Developers — Debug real-time message flows and check channel states directly from the terminal or IDE.
  • DevOps Engineers — Monitor application stats and manage API key security without leaving the command line.
  • Product Engineers — Test push notification payloads and presence logic during feature development.

Built-in capabilities (14)

batch_presence

Get presence for multiple channels

batch_publish

Publish messages to multiple channels at once

batch_push_publish

Publish batch push notifications

get_channel_metadata

Get metadata for a specific channel

get_message

Get a specific message by serial

get_messages

Retrieve message history for a channel

get_presence

Get current presence members for a channel

get_presence_history

Get presence history for a channel

get_stats

Retrieve application usage statistics

list_channels

Enumerate all active channels

publish_message

Publish a message to a specific channel

push_publish

Publish a direct push notification

revoke_tokens

Requires revocableTokens: true on the API key. Revoke Ably tokens before their expiry

update_message

Update, delete, or append to a message

Why Mastra AI?

Mastra's agent abstraction provides a clean separation between LLM logic and Ably tool infrastructure. Connect 14 tools through Vinkius and use Mastra's built-in workflow engine to chain tool calls with conditional logic, retries, and parallel execution. deployable to any Node.js host in one command.

  • Mastra's agent abstraction provides a clean separation between LLM logic and tool infrastructure. add Ably without touching business code

  • Built-in workflow engine chains MCP tool calls with conditional logic, retries, and parallel execution for complex automation

  • TypeScript-native: full type inference for every Ably tool response with IDE autocomplete and compile-time checks

  • One-command deployment to any Node.js host. Vercel, Railway, Fly.io, or your own infrastructure

M
See it in action

Ably in Mastra AI

AI AgentVinkius
High Security·Kill Switch·Plug and Play
Why Vinkius

Ably and 4,000+ other MCP servers. One platform. One governance layer.

Teams that connect Ably to Mastra AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.

4,000+MCP Servers ready
<40msCold start
60%Token savings
Raw MCP
Vinkius
Server catalogFind and host yourself4,000+ managed
InfrastructureSelf-hostedSandboxed V8 isolates
Credential handlingPlaintext in configVault + runtime injection
Data loss preventionNoneConfigurable DLP policies
Kill switchNoneGlobal instant shutdown
Financial circuit breakersNonePer-server limits + alerts
Audit trailNoneEd25519 signed logs
SIEM log streamingNoneSplunk, Datadog, Webhook
HoneytokensNoneCanary alerts on leak
Custom domainsNot applicableDNS challenge verified
GDPR complianceManual effortAutomated purge + export
Enterprise Security

Why teams choose Vinkius for Ably in Mastra AI

The Ably MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 14 tools execute in hardened sandboxes optimized for native MCP execution.

Your AI agents in Mastra AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

Ably
Fully ManagedVinkius Servers
60%Token savings
High SecurityEnterprise-grade
IAMAccess control
EU AI ActCompliant
DLPData protection
V8 IsolateSandboxed
Ed25519Audit chain
<40msKill switch
Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

The Vinkius Advantage

How Vinkius secures Ably for Mastra AI

Every tool call from Mastra AI to the Ably MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.

< 40msCold start
Ed25519Signed audit chain
60%Token savings
FAQ

Frequently asked questions

01

Can I see who is currently active in a specific channel?

Yes. Use the get_presence tool with the target Channel ID to retrieve a list of all members currently connected and their status.

02

How do I send a single message to multiple channels at once?

You can use the batch_publish tool. Provide a comma-separated list of channel IDs and the data payload to broadcast to all of them in one request.

03

Is it possible to retrieve the history of messages sent to a channel?

Absolutely. Use the get_messages tool to fetch the message history for any channel, with options to filter by timestamp or limit the number of results.

04

How does Mastra AI connect to MCP servers?

Create an MCPClient with the server URL and pass it to your agent. Mastra discovers all tools and makes them available with full TypeScript types.

05

Can Mastra agents use tools from multiple servers?

Yes. Pass multiple MCP clients to the agent constructor. Mastra merges all tool schemas and the agent can call any tool from any server.

06

Does Mastra support workflow orchestration?

Yes. Mastra has a built-in workflow engine that lets you chain MCP tool calls with branching logic, error handling, and parallel execution.

07

createMCPClient not exported

Install: npm install @mastra/mcp

Explore More MCP Servers

View all →