Show HN: An MCP server that runs 27 small web and open-data scrapers

A developer released TinyRex MCP, an MIT-licensed stdio Model Context Protocol server that exposes 27 public TinyRex Apify Store scrapers to MCP-capable AI agents such as Claude Desktop and Cursor using the user's own APIFY_TOKEN. The server provides two tools: list_actors, which returns each actor's name, title, description, Store URL and example input, and run_actor, which runs tinyrex/<name> with an input object, waits for completion and returns dataset items capped at 50 by default plus itemCount, runId and status. The actors are pay-per-event on Apify, with failed or empty runs often free under TinyRex pricing, and the package installs via pip from GitHub on Python 3.11+ or runs as a Docker image.

Run TinyRex https://apify.com/tinyrex Apify Store actors from any MCP-capable AI agent Claude Desktop, Cursor, and others using your own APIFY TOKEN . This is a thin stdio Model Context Protocol https://modelcontextprotocol.io/ server: it lists the public TinyRex actors and starts a run, then returns dataset items capped for MCP hosts . Actors are pay-per-event PPE on Apify. Failed or empty runs are often free under TinyRex pricing: check each actor’s Store page. You pay Apify with your own account; this MCP does not bill separately. Python 3.11+: pip install git+https://github.com/emirmrkaljevic/tinyrex-mcp.git or clone and: pip install -e . Requires an Apify API token https://console.apify.com/settings/integrations in the environment as APIFY TOKEN . { "mcpServers": { "tinyrex": { "command": "tinyrex-mcp", "env": { "APIFY TOKEN": "YOUR APIFY TOKEN" } } } } If the script is not on PATH , use the module form: { "mcpServers": { "tinyrex": { "command": "python", "args": "-m", "tinyrex mcp" , "env": { "APIFY TOKEN": "YOUR APIFY TOKEN" } } } } | Tool | What it does | |---|---| | list actors | Lists all 27 public TinyRex actors name, title, description, Store URL, example input . | | run actor | Runs tinyrex/<name with an input object, waits for the run, returns dataset items default max 50 plus itemCount , runId , and status. | 1. list actors → find gleif-lei-lookup 2. run actor with: { "actor": "gleif-lei-lookup", "input": { "companyNames": "Siemens AG" , "maxResultsPerName": 1 }, "max items": 5 } Private / ToS-blocked actors are not exposed. docker build -t tinyrex-mcp . docker run --rm -i -e APIFY TOKEN=YOUR APIFY TOKEN tinyrex-mcp python -m venv .venv && source .venv/bin/activate pip install -e . APIFY TOKEN=... tinyrex-mcp stdio MCP Smoke-test helpers list tools + one cheap run live in scripts/smoke test.py . MIT. Brand: TinyRex . Store username: tinyrex https://apify.com/tinyrex .