Multi-server support
Connect one or more MCP servers, including Apify's MCP server, so a single workflow can reach multiple tools and destinations.
MCP connectors
Apify’s MCP connectors collection links Apify Actors with apps and clients that support the Model Context Protocol. It is used to run Apify workflows and pass results into tools such as Slack, Notion, Telegram bots, and other MCP-enabled destinations.
Overview
MCP connectors is an Apify collection for connecting Apify Actors to apps and tools that support the Model Context Protocol. The collection page introduces it as a way to plug your Apify Actors into the apps you already use, with links to documentation and an announcement article for implementation details.
The collection highlights example Actors such as Telegram MCP Agent, Universal MCP Connector, and several workflow-specific connectors that send data to tools like Slack and Notion. On the companion Actor page, Apify describes the Universal MCP Connector as a way to run arbitrary workflows on Apify and publish the results to other MCP-supporting platforms.
What you can do with MCP connectors
Credential handling in the console
Use secure authentication stored in Apify Console rather than handling credentials inside the Actor code.
Connector setup from the run input
Choose an existing connector or create a new one from the Actor Input page, then point it at the target MCP server URL.
Prompt-driven orchestration
Use a custom query to steer the agent toward the right actions across connected MCP servers, such as creating an issue or sending a Slack message.
Primary or follow-up execution
Run the connector as a direct workflow driver or attach it as a post-processing step after another Actor finishes.
Result publishing to MCP-enabled tools
Publish results to other platforms that support the MCP protocol after Apify has run the workflow.
Common ways to use MCP connectors
Connect Actor output to downstream apps
Run an Apify Actor that gathers or transforms data, then hand the result to an MCP-enabled app for posting, summarizing, or updating a workspace.
Orchestrate multi-step workflows
Use the Universal MCP Connector as the main driver for a task that needs several steps across different MCP servers, such as fetching data, writing a summary, and sending it to Slack.
Add post-processing to an Actor run
Trigger a connector after another Actor finishes so the follow-up step can process the dataset, create a digest, or publish the output elsewhere.
Expose Apify workflows through chat
Build a Telegram bot or similar interface that lets people interact in plain language while an AI agent calls Apify MCP tools behind the scenes.
Publish results to team tools
Send scraped or curated data into tools like Notion or Slack when a workflow needs the result to land in a team workspace rather than stay in Apify.
Pros and Cons
Pros
- Connects Apify Actors to MCP-enabled apps and clients.
- Supports secure credential storage in Apify Console.
- Can work with one or multiple MCP servers at the same time.
- Can be used either directly or as a follow-up step after another Actor run.
- Apify offers both free and paid account options, so users can try the platform before committing.
Cons
- The collection page does not document a complete list of supported MCP clients or apps.
- The Universal MCP Connector page calls out current limitations around reliability, large datasets, and unanswered permission prompts.
- Using the Universal MCP Connector requires the OpenRouter Actor on your account.
FAQ
What are MCP connectors on Apify?
MCP connectors are part of the Apify platform and let you plug Apify Actors into apps and clients that support the MCP protocol. The source pages describe them as a way to run workflows on Apify and publish results to MCP-enabled tools, but they do not list a full compatibility matrix.
How can an MCP connector be used in a workflow?
The Universal MCP Connector can run arbitrary workflows on Apify and then publish results to other MCP-supporting platforms. The page also describes two ways to use it: directly as a primary workflow driver, or as a post-processing step after another Actor finishes.
How do you set up a connector for a target MCP server?
The product pages show setup through the Apify Console. You can select an existing connector or create a new one, then provide the MCP server URL and authenticate with OAuth, an API key, or a custom OAuth client when needed.
Is there pricing for using Apify Actors with MCP connectors?
Apify offers a free plan and paid subscription plans, and Actors in the Apify Store can be free or rented for a monthly fee specific to each Actor. Running them consumes platform usage credits included in the plan; excess usage is billed later.
What limitations should I know about?
The Universal MCP Connector page notes limitations such as occasional permission prompts that cannot yet be answered, low reliability of operations, and difficulty processing large datasets efficiently. It also requires running the OpenRouter Actor on your account.
Quick Facts
- Category
- AI Workflow
- Platform
- Apify
- Collection
- MCP connectors
- Source domain
- apify.com
- Primary use
- Connect Apify Actors to MCP-enabled apps and publish results
Alternativas a MCP connectors
CreateOS Sandbox
CreateOS Sandbox is an isolated compute environment for running code and agent workloads inside Firecracker micro-VMs. It is designed for workflows that need machine-level isolation, private networking between sandboxes, and programmatic control through SDK, CLI, or MCP.
AakarDev AI
AakarDev AI helps teams manage AI provider access, project-level setups, logs, and analytics from one dashboard. It supports BYOK workflows and lists providers including OpenAI, Google Gemini, Anthropic, Groq, Mistral AI, and Perplexity AI.
Arduino VENTUNO Q
Arduino VENTUNO Q is an edge AI computer for AI and robotics applications. It combines AI inference and deterministic control on a single board and is designed to work with Arduino App Lab.
ByteAsk
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repositories and verifies changes with the real compiler, debugger, sanitizers, and tests before showing a diff. It offers a free tier plus paid plans, with editor connectors and zero-retention handling described in the source.
Codex Plugins
Codex Plugins bundle reusable skills, app integrations, and MCP servers into workflows you can install in the Codex app or use from Codex CLI. They help extend Codex with connected-service tasks, reusable instructions, and shared team workflows.
hob
hob is an independent workspace for coding agents that keeps agent sessions, terminals, history, and follow-up work organized around the tools and providers you already use. It is aimed at developers who want local control over routing, history, and workspace structure rather than a bundled model stack.