MCP server

BIGHUB Official

io.bighub/mcp

Checked 26 Oct 2026, 08:31 UTC · Still published on its registry; checked against OSV.dev; never run by us

Decision learning for AI agent actions. Evaluate, score, decide, and learn from outcomes.

Runs on your computerVerified publisher: bighub.io

Website Source

At a glance

Type: MCP server
Publisher: bighub.io (verified by the MCP Registry)
Status: Runs on your computer
Sets up in: Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code
Last checked: 26 Oct 2026, 08:31 UTC

Connect it to your agent

Add to Cursor Add to VS Code VS Code Insiders

Opens the app, which shows the server and asks you to confirm. It then runs the package on your computer with your permissions. For other apps, copy the setup below.

Claude Code

claude mcp add bighub --env BIGHUB_API_KEY=YOUR_VALUE -- npx -y @bighub/bighub-mcp@0.2.1

Claude Desktop

{"mcpServers":{"bighub":{"command":"npx","args":["-y","@bighub/bighub-mcp@0.2.1"],"env":{"BIGHUB_API_KEY":"YOUR_VALUE"}}}}

Codex (config.toml)

[mcp_servers.bighub]
command = "npx"
args = ["-y","@bighub/bighub-mcp@0.2.1"]
env = { BIGHUB_API_KEY = "YOUR_VALUE" }

Gemini CLI

{"mcpServers":{"bighub":{"command":"npx","args":["-y","@bighub/bighub-mcp@0.2.1"],"env":{"BIGHUB_API_KEY":"YOUR_VALUE"}}}}

Cursor

{"mcpServers":{"bighub":{"command":"npx","args":["-y","@bighub/bighub-mcp@0.2.1"],"env":{"BIGHUB_API_KEY":"YOUR_VALUE"}}}}

VS Code

{"servers":{"bighub":{"type":"stdio","command":"npx","args":["-y","@bighub/bighub-mcp@0.2.1"],"env":{"BIGHUB_API_KEY":"YOUR_VALUE"}}}}

Runs on your computer with your permissions: check the package and its source before installing. Replace YOUR_VALUE with your own BIGHUB_API_KEY.

Related MCP servers

Decide Runtime
Evaluate supplied rules, save deterministic decisions, and read/export owned records. Paid pilot.
Agent Economic Trust
Outcome-calibrated economic trust gate for autonomous agents.
Trust Gate
Post-quantum, tamper-evident receipts for agent actions. Ed25519 + ML-DSA-65, offline verify.
Decision Integrity
Paid x402 evaluator for evidence, warrant, provenance, and represented action authority.
Overwing
Guardrails for LLM output: pass / fail / review verdicts and one recommended action. Hosted or npm.
NOT FOR HUMANS
Public NFH knowledge, ownership epochs, versioned learning, Odd Jobs, and unsigned preparation.
Agentstack
Deterministic reasoning stack for AI agents: simulate, decide & compute, plus cross-domain tools.
WhiteMagic — governed local memory for agent continuity
Governed local-first memory and continuity for AI agents — signed receipts, optional hosted lane.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.bighub/mcp.svg)](https://aptlynx.net/servers/io.bighub/mcp)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents