EmpirioLabs AI Search
Search the web with EmpirioLabs AI and get current results, one answer with its sources, or a research report with citations. Use when the user asks to look something up online, to find recent news, documentation, or sources, to answer a question with citations, or to research a topic in depth. Runs a bundled Python script that picks a search model from the live catalog (or the one you name) and prints the results or saves them to the path you choose.
EmpirioLabs AI web search
Search the web with the EmpirioLabs AI search API. The bundled script has three modes: search results, one answer with its sources, and a research report with citations.
Setup
- Create an API key at https://platform.empiriolabs.ai/dashboard/api-keys. Keys start with
sk-empiriolabs-. - Make the key available as
EMPIRIOLABS_API_KEYin the environment where commands run. Never paste the key into a prompt or a file in the project. - Python 3.8 or later. There is nothing to install.
Script paths below are relative to this skill's folder. On Windows, use python instead of python3.
Search
python3 scripts/search.py "latest stable release of Python"
Prints a numbered list of results, each with its title, URL, and a short extract:
1. Title of the first result
https://example.com/first-result
The opening lines of the page, shortened ...
Answer a question with sources
python3 scripts/search.py "who maintains the Model Context Protocol" --answer
Prints the answer, then the numbered sources it cites.
Research a topic
python3 scripts/search.py "state of solid-state batteries in 2026" --research --out ./battery-report.md
A research report reads many sources and can take several minutes. It costs more than a search, so confirm it with the user first. With --out, the script saves the report and prints a JSON summary:
{
"model": "MODEL_ID",
"file": "/home/me/project/battery-report.md",
"sources": 24,
"characters": 9120
}
Options
| Option | Meaning |
|---|---|
--answer | Return one answer with its sources. |
--research | Run a research report with citations. |
--model ID | Use a specific model. |
--param key=value | Any other model parameter, for example --param num_results=5. |
--out PATH | Save the output (with .json, the full result). |
--json | Print the full result as JSON. |
--overwrite | Replace an existing file. By default a numeric suffix is added instead. |
Choose a model and check prices
Search is billed per request, and the price depends on the model and the mode. Check before a run:
python3 scripts/search.py --list-models
python3 scripts/search.py --list-models --research
* marks the model used when --model is omitted. For a model's parameters, such as result count, date range, or domains to include, use the empiriolabs-models skill (models.py --show MODEL_ID).
Exit codes and errors
0success,1the request failed (the message says why),2invalid arguments.HTTP 401: the key is missing or invalid.HTTP 402: add credits at https://platform.empiriolabs.ai/dashboard/billing.
Other ways to connect
The same models are available through the EmpirioLabs AI remote MCP server at https://mcp.empiriolabs.ai/mcp (OAuth sign-in, or the API key as a bearer token). Setup: https://docs.empiriolabs.ai/mcp. API reference: https://docs.empiriolabs.ai.
Related skills
- Downloads
- Security audit
- Review
- Last updated
- 4d ago
- Current version
- v1.0.0
- License
- MIT-0
