Agent Harnesses runs on your own machine — the client starts it, so there is no endpoint to ping. 407 installs a week from pypi. Last commit 3 Nov 2026.
Agent-harness picks, decision guides, setup templates, and skills; live GitHub/HN discovery.
We read the source, 3 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.
r = subprocess.run(args["command"], shell=True, capture_output=True, text=True, timeout=300)
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
r = subprocess.run(args["command"], shell=True, capture_output=True, text=True, timeout=300)
r = subprocess.run(args["command"], shell=True, capture_output=True, text=True, timeout=300)
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 agent-harnesses -- uvx agent-harnesses-mcp
{
"mcpServers": {
"agent-harnesses": {
"command": "uvx",
"args": [
"agent-harnesses-mcp"
]
}
}
}
[mcp_servers.agent-harnesses]
command = "uvx"
args = ["agent-harnesses-mcp"]
{
"mcpServers": {
"agent-harnesses": {
"command": "uvx",
"args": [
"agent-harnesses-mcp"
]
}
}
}
{
"servers": {
"agent-harnesses": {
"type": "stdio",
"command": "uvx",
"args": [
"agent-harnesses-mcp"
]
}
}
}
Shared team memory for Claude Code: decisions, standards, and skills every agent session receives.
AI agent discovers MCP servers from GitHub npm - analyzes APIs configs
Bounded agent tools: time, hash, UUID, codec, JSON, request identity, and service discovery.
A package manager for Agent Skills — discover, vet, and pin them across Claude Code and Codex.
Live demand signals for idea validation: npm/PyPI downloads, GitHub + HN attention trends.
Search and fetch AI agent skills, rules files and MCP servers indexed from GitHub.
Drive the Cursor agent from Telegram, Discord, or GitHub — with images and voice notes.
Local-first MCP server for agent skills. Validate, lint, diff, and convert across IDEs.
Answers built from our own checks of this server.