Which integrations are available for this server?

Allows OpenAI Agents to make decisions based on information available on the web through UProc's data retrieval capabilities

How do I use UProc MCP?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@UProc MCP what are the latest features announced for React 19?" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

UProc MCP

Official UProc Model Context Protocol (MCP) server that enables referencing public web data. This server allows MCP clients like Claude Desktop, Cursor, Windsurf, OpenAI Agents and others make decisions based on the information available on the web.

Account setup

Make sure you have an account on uproc.io (new users get free credit for testing, and pay as you go options are available)
Get your API key from the user settings page

Related MCP server: Supabase MCP Server

Quickstart with Claude Desktop

Install nodejs to get the npx command (node.js module runner). Installation instructions can be found on the node.js website
Go to Claude > Settings > Developer > Edit Config > claude_desktop_config.json to include the following:

{ "mcpServers": { "UProc": { "command": "npx", "args": ["-y @uproc-io/mcp"], "env": { "API_TOKEN": "<insert-your-api-token-here>", } } } }

Other MCP clients

To use this MCP server with other agent types, you should adapt the following to your specific software:

the full command to run the MCP server is npx @uprocsaas/mcp
the environment variable API_TOKEN=<your-token> must exist when running the server

Usage

Some example queries that this MCP server will be able to help with:

Troubleshooting

Timeouts when using certain tools

Some tools can involve reading web data, and the amount of time needed to load the page can vary by quite a lot in extreme circumstances. To ensure that your agent will be able to conume the data, set a high enough timeout in your agent settings. A value of 180s should be enough for 99% of requests, but some sites load slower than others, so tune this to your needs.