MetaGO Agent Harness runs on your own machine — the client starts it, so there is no endpoint to ping. 507 installs a week from npm. Last commit 27 Oct 2026.
Decision lock, anti-hallucination, meta-evolution and provenance for any MCP agent. 55 tools.
We read the source, 6 d ago · rules 995398eba69f
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
'eval(', 'exec(', 'system(', 'rm -rf', 'del /f', 'format ', 'shutdown',
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.
const out = execSync(`${cmd} --help`, { encoding: 'utf8', timeout: 8000, stdio: 'pipe' });
const filePath = path.join(this.enginePath, file.path);
r = subprocess.run([exe, str(script)], capture_output=True, text=True,
var fn = (new Function('return (' + s + ')'))();
tbody.innerHTML = tools.map(t => {
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch MetaGO Agent Harness and you get told the day something new turns up.
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 metago -- npx -y @metago-ai/mcp-server
{
"mcpServers": {
"metago": {
"command": "npx",
"args": [
"-y",
"@metago-ai/mcp-server"
]
}
}
}
[mcp_servers.metago]
command = "npx"
args = ["-y", "@metago-ai/mcp-server"]
{
"mcpServers": {
"metago": {
"command": "npx",
"args": [
"-y",
"@metago-ai/mcp-server"
]
}
}
}
{
"servers": {
"metago": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@metago-ai/mcp-server"
]
}
}
}
LLM evals as MCP tools: score outputs for faithfulness, relevancy, and hallucination.
MCP adapter for Agent_Sudo: authorization, delegation, provenance, and audit for AI agents.
Live competitive-game predictions, meta data and decision tools for AI agents.
Context integrity for AI agents: evaluate freshness, confidence, provenance, and decision readiness.
Precision math engine for AI agents. 203 exact methods. Zero hallucination.
Cross-harness communication mesh for LLM agents — rooms, DMs, presence, and visibility over TCP
MCP compliance proxy between agent and tools: deterministic governance, fail-closed, audit trail.
Persistent memory, coordination, and learning for AI agents. Local-first, 25 MCP tools.
Answers built from our own checks of this server.