Context7
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Computer or cloud
AIRAS
Overview
Description from the maker (original English)
Automated AI research toolkit: hypothesis generation, experiments, and paper writing
PopNx MCP’s three pillars
These three are never merged into one score: opinions, measurements and popularity are different things.
- User voiceiNo reviews yetReviews open together with accounts in a later step
- Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
- UsageiVery new↓ 31/wk · ★ –
What you can do with it
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
- Connection: Runs on your computer
- Transport: stdio
- Category: Search & AI memory
Install
Pick the AI app you use, then copy the settings.
Before you install
- Basic checks: 1 of 1 passed
- Runs on your computer with your user’s permissions (files, network, apps).
- The registry lists no key to fill in.
You need
- PyPIPython’s uv installed (for the uvx command)
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"airas": {
"command": "uvx",
"args": [
"airas"
]
}
}
}Run this in your terminal
claude mcp add airas -- uvx airasOr copy the settings yourself
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"airas": {
"command": "uvx",
"args": [
"airas"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Or copy the settings yourself
Paste into .vscode/mcp.json in your project
{
"servers": {
"airas": {
"type": "stdio",
"command": "uvx",
"args": [
"airas"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
What it can do
Runs on your computer; the tool list appears in your AI app after you install it.
Basic checksi
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 8, 2026
- ✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account airas-org, which owns the repo
- … Not checked yet
Still maintained
We have not read this repo from GitHub yet
- … Not checked yet
Has a licence
We have not read this repo from GitHub yet
- – Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
- – Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
- … Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints
Compared with others in Search & AI memoryi
- More stars than 0% of the other 5722 servers in this category
- Published to the registry more recently than 50% of the other 5722 servers in this category
- Basic checks equal to or better than 100% of the other 5722 servers in this category
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
Common questions
Is AIRAS safe?
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
What keys or codes does it need?
The registry does not list a required key, though some servers ask you to sign in on first use.
Does it run on my computer or in the cloud?
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
Is it still maintained?
The GitHub repo last changed –, and the latest version (0.4.1) reached the registry 41 days ago.
Which apps can use it?
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.
What can I use instead?
In the same category: Context7, Codebase Memory, Exa
Alternatives
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Codebase Memory
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Runs on your computer
Exa
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Runs in the cloud✓ exa.ai
README from the maker
Open the README
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
AIRAS - an open-source project for research automation
AIRAS is open-source software for automated research. It gives a coding agent (Claude Code, Cursor, or any MCP client) everything it needs to take a research topic through literature survey, hypothesis, experiments, and a finished paper, and it makes the paper's claims verifiable: the paper is preregistered in git before any experiment runs, every reported number is realized from run outputs, and CI re-checks all of it before the PDF of record is produced.
AIRAS ships as one PyPI package (airas) that provides:
- an MCP server with the research tools the flow needs (paper search, hypothesis and experimental design, experiment results, figure rendering, LaTeX, Overleaf, and the record/verification tools),
- a Claude Code plugin that bundles the server with the
auto-researchworkflow skills, - a small CLI (
airas verify-record,airas verify-paper) that the experiment repository's CI uses as the verification gate.
Currently, it focuses on the automation of machine learning research.
Quick Start
No clone, no Docker. Only uv is required; uvx fetches the package on first run.
1. Install
AIRAS is meant to be driven from Claude Code through its plugin. The plugin installs the MCP server together with the auto-research workflow skills and the hooks that record the agent's state:
/plugin marketplace add airas-org/airas/plugin install airas@airas
The MCP server can also be used on its own, without the skills and hooks. In Claude Code:
claude mcp add airas -- uvx airasIn any other MCP client, add it to the client's MCP configuration (e.g. .mcp.json):
{"mcpServers": { "airas": { "command": "uvx", "args": ["airas"] } } }
Upgrading. uvx keeps the version it fetched the first time, so an existing install does not move to a new release on its own. Run uv cache clean airas (or uvx airas@latest) once to pick up the latest version.
2. Configure credentials
Credentials live in ~/.airas/credentials.json and are re-read on every tool call, so you can create or edit the file at any time:
mkdir -p ~/.airascat > ~/.airas/credentials.json <<'EOF' { "GH_PERSONAL_ACCESS_TOKEN": "ghp_...", "SEYVAL_API_KEY": "..." } EOF chmod 600 ~/.airas/credentials.json
| Key | Purpose |
|---|---|
GH_PERSONAL_ACCESS_TOKEN | Required. Creates and drives the experiment repository (repo + workflow scopes, admin on the repository). |
SEYVAL_API_KEY (+ optional SEYVAL_COMPUTE_ID, SEYVAL_WORKSPACE_ID) | Needed for backend="seyval": running experiments on the Seyval compute platform and cross-checking their provenance. See Execution platforms. |
OPENAI_API_KEY / ANTHROPIC_API_KEY / GEMINI_API_KEY / OPENROUTER_API_KEY / AWS_BEARER_TOKEN_BEDROCK / VERCEL_AI_GATEWAY_API_KEY | Not needed for the flow: the agent driving AIRAS authors every artifact itself, guided by the skills, and get_prompts provides the authoring guidance for a step when you write it yourself. A key is only used when you call the backend-LLM tools (analyze_experiment, verify_paper_values with a model) directly. |
3. Start a research project
In Claude Code, invoke the orchestrator skill and give it a topic:
/airas:auto-researchIt walks through the flow below, asking you to settle the operational choices (repository visibility, execution platform, compute target) once up front. Other MCP clients call the tools directly; each tool's description says what comes before and after it, and the MCP documentation walks the flow.
The auto-research flow
auto-research owns only the ordering and the rules that span steps. Each step is its own skill with a stated contract, so you can also invoke a single step on an existing repository.
| Step | Skill | What it leaves in the repository |
|---|---|---|
| 1 | setup-repository | An experiment repository created from airas-template, cloned, with Actions secrets provisioned and main protected. All research state lives here from now on. |
| 2 | search-papers | Papers found across sources, including airas-papers-db, and their full text downloaded for the next step to read. |
| 3 | hypothesize-and-design | A falsifiable hypothesis and an experimental design that fixes run ids, metrics, models, datasets, and the compute environment. |
| 4 | preregister-paper | The full paper, written before any experiment, as numbered claims with criteria and predicted intervals. Its commit is the freeze point; .research/record.json is created here. |
| 5 | write-experiment-code | Experiment code against a fixed execution contract (Hydra entrypoint, sanity / pilot / full modes), environment fixed by lockfile and Dockerfile. Metrics are produced by airas-eval, not by the code itself. |
| 6 | run-experiments | Runs executed on the chosen backend (GitHub Actions or Seyval), outputs brought back under .research/results/ with provenance. See Execution platforms. |
| 7 | analyze-results | The analysis and verifiable figures (Vega-Lite charts, text-defined diagrams). |
| 8 | publish-paper | Every stated number realized from the record, compile and verification green locally, then pushed. CI re-runs the verification and commits paper.pdf to the protected branch: the paper of record. |
What the flow guarantees
- Declare before you run. Nothing is dispatched before the preregistration commit exists, and every run descends from it. Fixes are committed on top, never rebased away.
- The record only grows.
.research/record.jsonis an append-only tree of hypotheses, claims, designs, runs, and results. A reworded claim, a changed run condition, or a dropped result all fail the same check. A claim that misses its criterion is reported as a negative result, not rewritten. - No experimental number is ever typed. Numbers reach the paper only through
\airasval{...}references to a run's measured metric or declared parameter, rendered from the record. Anything else is marked\unverified{...}. - The gate is enforced, not advisory. Branch protection makes the verification workflow a required check, so a red run cannot be pushed past.
- The repository is the state. Everything a later step needs is committed, so a fresh session can resume from the clone alone.
Execution platforms and LLMs
Experiments run through the same three MCP tools on either backend: dispatch_experiment starts the run, get_experiment_run_status follows it, and import_run_outputs copies its outputs from where the backend keeps them (Seyval's storage, or the workflow's artifact on GitHub Actions) into .research/results/ with a provenance manifest. The record gate cross-checks the committed bytes against that same store, and once the store has dropped the run, against the sha256 hashes the import recorded. Seyval (bring-your-own Slurm compute) and GitHub Actions are supported; a backend for machines you run yourself (RunPod, a lab cluster) is not yet, since it needs a store the agent cannot rewrite.
The flow needs no LLM key: the agent authors the hypothesis, design, analysis and paper itself, guided by the skills. Backend-LLM tools (analyze_experiment, and verify_paper_values with a model) and get_prompts, which hands a client the prompts they use, exist for use outside the flow; the former need a provider key (get_available_llms lists the models your keys allow). Supported providers: OpenAI, Anthropic, Google Gemini, OpenRouter, Amazon Bedrock, and Vercel AI Gateway.
Companion repositories
AIRAS relies on three sibling repositories under the airas-org organization. Each keeps one piece of the workflow outside the agent's reach.
| Repository | Role |
|---|---|
| airas-template | The template every experiment repository is created from. It ships the CI workflows, the execution contract, and the verification gate. |
| airas-papers-db | A curated database of papers from top conferences that the agent can search through search_papers, alongside OpenAlex, Semantic Scholar, and arXiv. |
| airas-eval | The evaluation logic, in one place. Metrics are computed by airas-eval from the run's evaluation inputs, not by the experiment code, so the agent cannot tamper with its own scores. |
MCP tools
The auto-research flow uses the following tools; the skills above are thin contracts over them. The server exposes more, but these are the ones a research project goes through.
| Step | Tools |
|---|---|
setup-repository | prepare_repository, set_github_actions_secrets |
search-papers | search_papers, dispatch_literature_fetch |
hypothesize-and-design | get_prompts, retrieve_models, retrieve_datasets, search_huggingface_hub |
preregister-paper | preregister_record, get_prompts, append_to_record, update_record, verify_latex |
write-experiment-code | get_prompts, get_library_docs |
run-experiments | dispatch_experiment, get_experiment_run_status, import_run_outputs, fetch_experiment_results |
analyze-results | fetch_experiment_results, analyze_experiment / get_prompts, render_chart, render_diagram, append_to_record, update_record |
publish-paper | verify_record, verify_paper_values, verify_latex, open_in_overleaf, get_workflow_runs |
See the MCP documentation for descriptions, credentials per tool, and configuration options.
CLI
uvx airas # MCP server on stdio (default)uvx airas verify-record # check .research/record.json against run outputs, git history, and the platform uvx airas verify-paper # check paper values and citations against the record and run outputs — no PDF build uvx airas verify-record --implementation-verifier-model # review implementation against declared designs uvx airas verify-paper --citation-verifier-model # judge unjudged passage citations uvx airas publish-paper # build the paper's PDF for publishing (values already verified by the gate)
verify-record checks declarations and execution evidence; verify-paper independently checks the paper against them. They are the two required checks the experiment repository's CI runs on the protected branch; publish-paper builds the PDF in the separate, non-required publish workflow.
Development
cd backenduv sync uv run airas
Lint and type checks are wired through pre-commit (pre-commit install once per clone). See CONTRIBUTING.md.
Roadmap
AIRAS is developed in stages. Reliability comes first: an automated research pipeline is only worth scaling once its outputs can be trusted and reproduced.
1. Reliability (in progress). The record now guarantees that every number in the paper traces back to a declared run and its outputs, that each claim's verdict is derived from the criterion it declared
Only the beginning is shown; read the rest in the repo