tinyrex-mcp
Python stdio MCP server that lets any MCP client list and run 27 small TinyRex scrapers on Apify (remote jobs from 6 boards, Shopify store catalogs and app detection, audio and video transcription, company registers, tenders) with your own APIFY_TOKEN and returns the dataset rows. MIT licensed. I built and maintain it.
Documentation
tinyrex-mcp
Run 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 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.
Install
Python 3.11+:
pip install git+https://github.com/emirmrkaljevic/tinyrex-mcp.git
# or clone and:
# pip install -e .
Requires an Apify API token in the environment as APIFY_TOKEN.
Claude Desktop / Cursor (mcpServers)
{
"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"
}
}
}
}
Tools
| 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. |
Example: LEI lookup
list_actors→ findgleif-lei-lookuprun_actorwith:
{
"actor": "gleif-lei-lookup",
"input": { "companyNames": ["Siemens AG"], "maxResultsPerName": 1 },
"max_items": 5
}
Public actors wrapped
Private / ToS-blocked actors are not exposed.
Docker (stdio)
docker build -t tinyrex-mcp .
docker run --rm -i -e APIFY_TOKEN=YOUR_APIFY_TOKEN tinyrex-mcp
Development
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.
License
MIT. Brand: TinyRex. Store username: tinyrex.