Aurora runs on your own machine — the client starts it, so there is no endpoint to ping. 174 installs a week from pypi. Last commit 31 Aug 2026.
Glass-box statistical analysis for agents: 19 methods, cited findings, measured error rates.
We read the source, 3 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.
__import__(opt_mod)
proc = subprocess.run(
Select a range with headers + numeric data, then click Analyze.
for sub in sorted(root.iterdir()):
out.innerHTML = j.results.map(r => `
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 aurora -- uvx aurora-mcp
{
"mcpServers": {
"aurora": {
"command": "uvx",
"args": [
"aurora-mcp"
]
}
}
}
[mcp_servers.aurora]
command = "uvx"
args = ["aurora-mcp"]
{
"mcpServers": {
"aurora": {
"command": "uvx",
"args": [
"aurora-mcp"
]
}
}
}
{
"servers": {
"aurora": {
"type": "stdio",
"command": "uvx",
"args": [
"aurora-mcp"
]
}
}
}
Local-first LLM cost analysis and model-switch savings estimates for AI agents.
Evidence-gated verification, selection, and measurement MCP for coding agents.
Search and share cited agent findings. Public reads; authenticated writes.
MCP server for Java call graph generation, static analysis, method chains & config management
MCP server for Instagit — AI-powered Git repository analysis for coding agents
Test generation, mocks, coverage analysis for AI agents
MCP server for fixing static analysis issues from SARIF reports with AI agents
Failure-memory layer for coding agents: search evidence-rated failure lessons by error text.
Answers built from our own checks of this server.