Argus — Testing for Coding Agents runs on your own machine — the client starts it, so there is no endpoint to ping. 3 744 installs a week from pypi. Last commit 28 Oct 2026.
Testing MCP for coding agents: exercise real user journeys, find bugs, verify them with evidence.
We read the source, 5 d ago · rules 995398eba69f
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
subprocess.run(
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.
subprocess.run(
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
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 argus -- uvx argus-testing
{
"mcpServers": {
"argus": {
"command": "uvx",
"args": [
"argus-testing"
]
}
}
}
[mcp_servers.argus]
command = "uvx"
args = ["argus-testing"]
{
"mcpServers": {
"argus": {
"command": "uvx",
"args": [
"argus-testing"
]
}
}
}
{
"servers": {
"argus": {
"type": "stdio",
"command": "uvx",
"args": [
"argus-testing"
]
}
}
}
Debugging experiments for coding agents: reproduce failures and verify fixes with test evidence.
Browser-backed QA with evidence and fix-ready reports for coding agents.
Evidence-first browser QA with read-only MCP server for AI agent debugging.
Parallel-burst abuse testing for agent APIs with replayable evidence packs.
Shared memory and mail for your AI agents. Verified with Claude Code; other MCP clients in testing.
Read-only evidence for the tools agents run: MCP server records, coverage and policy.
Test a web app in a real browser from plain English. Passed, failed or cannot verify, with evidence.
Colter audits product pages for AI shopping agents and returns fixes, tests, and Evidence Packs.
Answers built from our own checks of this server.