IRP runs on your own machine — the client starts it, so there is no endpoint to ping. 91 installs a week from pypi. Last commit 23 Oct 2026.
Turn a research paper into working code and prove, claim by claim, how close it gets.
We read the source, 1 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
result = subprocess.run(
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add irp -- uvx irp-agents
{
"mcpServers": {
"irp": {
"command": "uvx",
"args": [
"irp-agents"
]
}
}
}
[mcp_servers.irp]
command = "uvx"
args = ["irp-agents"]
{
"mcpServers": {
"irp": {
"command": "uvx",
"args": [
"irp-agents"
]
}
}
}
{
"servers": {
"irp": {
"type": "stdio",
"command": "uvx",
"args": [
"irp-agents"
]
}
}
}
Research intelligence for AI coding agents. 2M+ CS papers with evidence and tradeoffs.
Turn an idea into a device anyone can build: parts, printed parts, wiring, code and a picture guide.
Read-only tools that check whether code, and the tests that claim it works, are real.
Turn a GitHub repo or docs site into agent-ready context: pack it or search it, over MCP.
MCP server connecting Claude Code to GitHub for an issue to branch to PR to close workflow.
Turn Lighthouse audits into coding-agent fix packs for Claude Code, Cursor, and Copilot.
One call, one paper: everything openly available around it — full text, license, datasets, code…
Step-by-step workflows for ChatGPT, Claude and Claude Code: the AI gets one step at a time.
Answers built from our own checks of this server.