BIGHUB runs on your own machine — the client starts it, so there is no endpoint to ping. 82 installs a week from npm. Last commit 16 May 2026.
Decision learning for AI agent actions. Evaluate, score, decide, and learn from outcomes.
Nothing serious here today
Today is the operative word: we check BIGHUB every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
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 mcp -e 'BIGHUB_API_KEY=<BIGHUB_API_KEY>' -- npx -y @bighub/bighub-mcp{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@bighub/bighub-mcp"
],
"env": {
"BIGHUB_API_KEY": "<BIGHUB_API_KEY>"
}
}
}
}[mcp_servers.mcp]
command = "npx"
args = ["-y", "@bighub/bighub-mcp"]
env = { BIGHUB_API_KEY = "<BIGHUB_API_KEY>" }{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@bighub/bighub-mcp"
],
"env": {
"BIGHUB_API_KEY": "<BIGHUB_API_KEY>"
}
}
}
}{
"servers": {
"mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@bighub/bighub-mcp"
],
"env": {
"BIGHUB_API_KEY": "<BIGHUB_API_KEY>"
}
}
}
}Put your own value in place of
<BIGHUB_API_KEY> (BIGHUB API key for authenticating requests (X-API-Key header)).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
BIGHUB_BEARER_TOKEN (Alternative authentication via Bearer token. Use this or BIGHUB_API_KEY), BIGHUB_BASE_URL (BIGHUB API base URL).
Alternatives to BIGHUB
same job, measured the same wayDecision tracking with prediction validation and outcome gates for AI agents
Tamper-evident decision audit trail and outcome-weighted memory for AI trading agents.
Score any AI for trust across 10 dimensions; evaluate, monitor & govern LLMs and agents.
Self-learning memory for AI coding agents with pattern detection and confidence scoring.
Typed AI decisions for agents: classify, route, screen evidence, score and batch-label text.
Explainable ALLOW/WARN/BLOCK risk decisions for AI agent actions before execution, signed as OAA.
Decision memory for AI coding agents: captures decisions once, briefs every agent before it acts.
Evaluate an MCP server with scout and verify scout attestations, from inside the agent. Read-only.
BIGHUB — questions
Answers built from our own checks of this server.