AIRAS — Claude Code MCP server: what it does, how to install
Automates machine learning workflows from academic paper review to final publication. Pre-registers hypotheses in Git and validates numerical metrics via CI.
claude mcp add airas -- uvx airasWhat AIRAS does
The server gives your coding assistant specialized tools for running automated ML studies. The agent searches literature, outlines falsifiable hypotheses, drafts experiment scripts using Hydra, and schedules test runs through GitHub Actions or the Seyval compute platform.
Every experiment step logs directly to .research/record.json. Reported figures link into LaTeX manuscripts with the \airasval{...} macro, preventing manual data entry errors. The workflow mandates preregistration: paper drafts and criteria commit to Git before runs dispatch, while CLI utilities like airas verify-record confirm consistency in CI.
Running the package requires uv on your path and a GH_PERSONAL_ACCESS_TOKEN stored in ~/.airas/credentials.json with repo and workflow scopes. Without GitHub credentials configured, the assistant cannot create and configure the study repository.
What it helps with
- automate the machine learning research loop from literature survey to paper draft
- commit study hypotheses to git prior to initiating test runs
- insert validated experiment metrics into latex manuscripts automatically
- validate reproducibility of research figures and numbers in continuous integration
Example prompts for the agent
- Search recent publications on sparse attention and prepare the initial experimental design
- Preregister our hypothesis commit and generate the project repository
- Extract the latest test results, build Vega-Lite plots, and insert the metrics into paper.tex
How to install AIRAS
Platform CLI
claude mcp add airas -- uvx airasuvx runs the command named after the package; if the README names another one, use uvx --from airas <command>
Platform CLI
codex mcp add airas -- uvx airasuvx runs the command named after the package; if the README names another one, use uvx --from airas <command>
Config file
{
"mcpServers": {
"airas": {
"command": "uvx",
"args": [
"airas"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from airas <command>
Config file
{
"servers": {
"airas": {
"type": "stdio",
"command": "uvx",
"args": [
"airas"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from airas <command>
Platform CLI
gemini mcp add airas uvx airasuvx runs the command named after the package; if the README names another one, use uvx --from airas <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about AIRAS
How do I install AIRAS in Claude Code?
Run claude mcp add airas -- uvx airas in your terminal. You must have the uv tool installed on your system first.
What does the AIRAS MCP server do?
It provides an agent with tools to discover literature, design reproducible ML tests, render charts, and compile papers. It guarantees that published metrics trace back to verifiable execution outputs.
What API credentials does AIRAS require?
You need a GH_PERSONAL_ACCESS_TOKEN with repo and workflow scopes inside ~/.airas/credentials.json. An optional SEYVAL_API_KEY is needed only when dispatching jobs to Seyval compute clusters.
