Dataset MCP Uploader

Pricing

Rating

Developer

Actor stats

Categories

Share

Dataset MCP Uploader allows you to process datasets on the Apify platform and then publish the results on other platforms that support MCP protocol (most popular platforms do).

[!WARNING]
Don't choose state of the art LLMs to process large datasets as it can burn through your Apify credits. Experiment first with smaller workflows or cheaper (default) models.

Features

• Secure authentication by setting your API key or OAuth for the target MCP server directly in Apify Console. This Actor doesn't need to handle any credentials.
• Connect one or multiple MCP servers at the same time, Apify MCP server is supported by default.
• Steer the agent with a custom query to choose appropriate actions across connected MCP servers (e.g. "on failing Actor run, create an issue on GitHub and send me message to Slack").
• LLM tokens are charged directly to your Apify account credits via OpenRouter Actor, no need to have account on OpenAI or Anthropic.
• Automatic model selection via OpenRouter, which chooses the best model for your use case based on performance and cost.

Authorization

MCP connector credentials are stored securely inside Apify Console and are never exposed to the Actor code. You only need to set up the connection to your MCP server once in Apify Console and then you can use it in any Actor that supports MCP connectors.

Once on the Actor Input page:

1. Choose an existing MCP connector or click on "Create new connector".
2. Fill in the MCP server URL, the input will automatically highlight if you can use OAuth directly (via dynamic client registration).
3. If OAuth is not available, you can provide an API key or create your own OAuth client on the target platform.
4. Once you create the connector, it will be available for all Actors that support MCP connectors.

How to run

You can use this connector either as primary workflow driver or as a post-processing step after running your main Actor.

Directly

Use prompt that suggests what data you need or what Actor to call. You can also process your stored data directly.

Example prompt: Check the dataset for top restaurants. Send me the summary to Slack channel #sushi-recommendations.

As an integration

Attach this Actor as integration that runs after your main Actor finishes. You can use the payload template variables to pass any metadata from your main Actor run to the prompt of the MCP Connector.

Current limitations

These limitations are expected to be resolved in the future

• Agents sometimes asks for permission but there is no way to answer it back.
• Processing large datasets is not optimal as growing context can lead to inaccuracy or it might be too expensive. We expect this to improve with better pre-processing tools.
• Requires to run the OpenRouter Actor on your account that requires small amount of memory

Debugging

Tool calls results and agent messages are stored in the key-value store of each run.