BIGHUB

NPM · @BIGHUB/BIGHUB-MCP · SCANNED AUG 3

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

Available components

+16 this week 59 59 Trust /100

Trust breakdown (6 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score →

Supply Chain Security86

No malware found by supply-chain analysis.Pass
Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.Partial
No install/post-install scripts declared.Pass
Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree. View diagnostics → Partial

Provenance & Transparency45

Source repository is publicly reachable at the declared URL. View diagnostics → Pass
Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
Clear OSI-approved license (MIT).Pass
Actively maintained (last published 131 days ago).Pass
Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail

Schema Quality & AI Usability37

AI-judged instruction clarity (poor).Fail
Tool/resource definitions use about 5931 tokens (~47/item across 125 items; 125 tools + 0 resources), lean.Pass
Usage-examples check failed: none of the tools include examples. See how to fix → Fail

Stability & Change Management27

Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial

Tool Coverage75

100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
11% of tool parameters carry a description.Partial
Structured output schemas are declared (64% of tools); any adoption earns full credit.Pass

Capabilities100

Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass

Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · @bighub/bighub-mcp

Claude Codex opencode OpenClaw Hermes Other

# add to Claude Code

claude mcp add io-bighub-mcp -- npx -y @bighub/bighub-mcp

# add to Codex CLI

codex mcp add io-bighub-mcp -- npx -y @bighub/bighub-mcp

// opencode.json

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-bighub-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@bighub/bighub-mcp"
      ],
      "enabled": true
    }
  }
}

# add to OpenClaw

openclaw mcp add io-bighub-mcp --command npx --arg -y --arg @bighub/bighub-mcp

# ~/.hermes/config.yaml

mcp_servers:
  io-bighub-mcp:
    command: "npx"
    args: ["-y", "@bighub/bighub-mcp"]

// mcp.json

{
  "mcpServers": {
    "io-bighub-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@bighub/bighub-mcp"
      ]
    }
  }
}

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

3 Aug 26 +1

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
2 Aug 26 +10
- Known CVEs: unverified → partial ▲ security
- Stability: unverified → 0.23 ▲ functional
- Dependency health: unverified → partial ▲ functional
1 Aug 26 +15
- Malware scan: unverified → pass ▲ security
31 Jul 26 −3
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
30 Jul 26 −30
- Malware scan: pass → unverified ▼ security
- Known CVEs: partial → unverified ▼ security
- Dependency health: partial → unverified ▼ functional
29 Jul 26 +23
- Provenance: unverified → fail ▼ security
- Install scripts: unverified → pass ▲ security
- Known CVEs: unverified → partial ▲ security
- Schema quality: unverified → poor ▲ functional
- Maintenance: unverified → pass ▲ functional
- Dependency health: unverified → partial ▲ functional
- License: unverified → pass ▲ functional
- Licence: MIT functional
27 Jul 26 43

First indexed and scored.

Show 2 earlier entries Hide earlier entries

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 3 Aug 2026 · Analysed npm/@bighub/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 94 packages

94 packages in the resolved dependency tree · 94 deprecated · 29 stale.

The dependency tree was only partially resolved, so these counts may be incomplete.

MCP tools — 125 exposed · ~5,931 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.

Tool Tokens

bighub_actions_dashboard_summary ~17

Get action dashboard summary.

Input Output Examples

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

bighub_actions_dry_run ~49

Dry-run action evaluation (non-persistent) via /actions/evaluate with dry_run=true.

Input Output Examples

Name	Type	Req	Description
idempotency_key	string	—	—
payload	object	yes	—

No output schema declared.

No examples provided.

bighub_actions_evaluate ~94

Evaluate an action via /actions/evaluate — returns decision intelligence (recommendation, risk, trajectory health, alternatives).

Input Output Examples

Name	Type	Req	Description
action	string	yes	—
actor	string	—	—
context	object	—	—
domain	string	—	—
idempotency_key	string	—	—
metadata	object	—	—
target	string	—	—
value	number	—	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_actions_evaluate_batch ~71

Evaluate multiple actions in a single request via /actions/evaluate/batch. Each element follows the same schema as bighub_actions_evaluate. Max 100 actions. Rate limited: 10/min.

Input Output Examples

Name	Type	Req	Description
actions	array	yes	—
idempotency_key	string	—	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_actions_evaluate_payload ~44

Evaluate an action with full decision intelligence payload via /actions/evaluate.

Input Output Examples

Name	Type	Req	Description
idempotency_key	string	—	—
payload	object	yes	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_actions_live_connect ~45

Open a concurrent live agent connection slot. Returns connection_id to reuse for heartbeats and submits.

Input Output Examples

Name	Type	Req	Description
actor	string	—	—
context	object	—	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_actions_live_disconnect ~38

Disconnect a live agent connection, freeing the slot immediately.

Input Output Examples

Name	Type	Req	Description
connection_id	string	yes	—
context	object	—	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_actions_live_heartbeat ~51

Heartbeat an existing live agent connection to keep it alive (recommended every 40s, TTL 120s).

Input Output Examples

Name	Type	Req	Description
connection_id	string	yes	—
context	object	—	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_actions_memory_context ~64

Read decision memory context window and rates.

Input Output Examples

Name	Type	Req	Description
actor	string	—	—
domain	string	—	—
limit_recent	integer	—	—
source	string	—	—
tool	string	—	—
window_hours	integer	—	—

No output schema declared.

No examples provided.

bighub_actions_memory_ingest ~89

Ingest scored execution events into decision memory.

Input Output Examples

Name	Type	Req	Description
actor	string	—	—
domain	string	—	—
events	array	yes	—
model	string	—	—
redact	boolean	—	—
redaction_policy	string	—	—
source	string	—	—
source_version	string	—	—
trace_id	string	—	—

No output schema declared.

No examples provided.

bighub_actions_memory_recommendations ~126

Compute decision memory recommendations.

Input Output Examples

Name	Type	Req	Description
actor	string	—	—
auto_apply	boolean	—	—
domain	string	—	—
include_examples	boolean	—	—
limit_recommendations	integer	—	—
min_approval_rate	number	—	—
min_blocked_rate	number	—	—
min_events	integer	—	—
min_tool_error_rate	number	—	—
scope	object	—	—
source	string	—	—
tool	string	—	—
window_hours	integer	—	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_actions_memory_refresh_aggregates ~35

Refresh decision memory aggregates.

Input Output Examples

Name	Type	Req	Description
concurrent	boolean	—	—
window_hours	integer	—	—

No output schema declared.

No examples provided.

bighub_actions_observer_stats ~18

Get action observer stats.

Input Output Examples

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

bighub_actions_status ~16

Get action system status.

Input Output Examples

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

bighub_actions_verify_validation ~28

Verify a previous evaluation by validation_id.

Input Output Examples

Name	Type	Req	Description
validation_id	string	yes	—

No output schema declared.

No examples provided.

bighub_api_keys_create ~24

Create an API key.

Input Output Examples

Name	Type	Req	Description
payload	object	yes	—

No output schema declared.

No examples provided.

bighub_api_keys_delete ~34

Delete or revoke an API key.

Input Output Examples

Name	Type	Req	Description
key_id	string	yes	—
reason	string	—	—

No output schema declared.

No examples provided.

bighub_api_keys_list ~25

List API keys.

Input Output Examples

Name	Type	Req	Description
include_revoked	boolean	—	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_api_keys_rotate ~25

Rotate an API key.

Input Output Examples

Name	Type	Req	Description
key_id	string	yes	—

No output schema declared.

No examples provided.

bighub_api_keys_scopes ~19

List available API key scopes.

Input Output Examples

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

bighub_api_keys_validate ~33

Validate an API key (query + X-API-Key header).

Input Output Examples

Name	Type	Req	Description
api_key	string	yes	—

No output schema declared.

No examples provided.

bighub_approvals_list ~33

List approval queue items.

Input Output Examples

Name	Type	Req	Description
limit	integer	—	—
status_filter	string	—	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_approvals_resolve ~41

Resolve an approval request.

Input Output Examples

Name	Type	Req	Description
comment	string	—	—
request_id	string	yes	—
resolution	string	yes	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_auth_login ~26

Authenticate and return access/refresh tokens.

Input Output Examples

Name	Type	Req	Description
payload	object	yes	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_auth_logout ~25

Invalidate a refresh token.

Input Output Examples

Name	Type	Req	Description
refresh_token	string	—	—

No output schema declared.

No examples provided.

bighub_auth_refresh ~26

Rotate auth tokens with refresh token.

Input Output Examples

Name	Type	Req	Description
refresh_token	string	—	—

No output schema declared.

No examples provided.

bighub_auth_signup ~27

Input Output Examples

Name	Type	Req	Description
payload	object	yes	—

No output schema declared.

No examples provided.

bighub_calibration_breakdown ~25

Calibration breakdown by dimension.

Input Output Examples

Name	Type	Req	Description
by	string	—	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_calibration_drift ~34

Detect calibration drift over time.

Input Output Examples

Name	Type	Req	Description
domain	string	—	—
window_days	integer	—	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_calibration_feedback ~25

Calibration feedback and improvement suggestions.

Input Output Examples

Name	Type	Req	Description
domain	string	—	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_calibration_observe ~86

Submit a calibration observation (predicted risk vs real outcome).

Input Output Examples

Name	Type	Req	Description
action	string	—	—
actor_type	string	—	—
case_id	string	yes	—
domain	string	—	—
outcome_status	string	yes	—
predicted_risk	number	yes	—
tool	string	—	—
verdict	string	—	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_calibration_quality_history ~57

Daily quality score over time — powers the Learning chart. Returns quality_score (1 − Brier), positive_rate per day.

Input Output Examples

Name	Type	Req	Description
days	integer	—	Number of days to include
domain	string	—	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_calibration_reliability ~33

Calibration reliability diagram data.

Input Output Examples

Name	Type	Req	Description
domain	string	—	—
tool	string	—	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_calibration_report ~47

Calibration report: how well do predicted risk scores match real outcomes.

Input Output Examples

Name	Type	Req	Description
domain	string	—	—
risk_band	string	—	—
tool	string	—	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_cases_calibration ~30

Get calibration metrics (prediction vs reality) for cases.

Input Output Examples

Name	Type	Req	Description
domain	string	—	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_cases_create ~158

Create a decision case. Requires action and verdict.

Input Output Examples

Name	Type	Req	Description
action	object	yes	Action payload: {tool, action, arguments, value, target, domain}
actor_id	string	—	—
actor_type	string	—	—
agent_model	string	—	—
context	object	—	—
domain	string	yes	—
goal_summary	string	—	—
refs	object	—	—
simulation	object	—	—
tags	array	—	—
trigger_source	string	—	—
verdict	object	yes	Required verdict: {verdict: ALLOWED\|BLOCKED\|APPROVAL_REQUIRED\|LIMITED\|DRY_RUN, mode, reasons, risk_score, confidence}

Structured output declared, but exposes no named fields.

No examples provided.

bighub_cases_get ~26

Get a decision case by ID.

Input Output Examples

Name	Type	Req	Description
case_id	string	yes	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_cases_list ~96

List decision cases with filters.

Input Output Examples

Name	Type	Req	Description
action	string	—	—
domain	string	—	—
has_outcome	boolean	—	—
limit	integer	—	—
max_risk_score	number	—	—
min_risk_score	number	—	—
offset	integer	—	—
outcome_status	string	—	—
tool	string	—	—
verdict	string	—	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_cases_precedents ~103

Get precedent intelligence for a proposed action. action must be a nested ActionInput object.

Input Output Examples

Name	Type	Req	Description
action	object	yes	ActionInput: {action, tool, action_type, arguments, value, target}
context	object	—	ContextInput: {axes, axes_risk_score, intent, irreversibility}
domain	string	—	Domain to scope precedent search
limit	integer	—	—
min_similarity	number	—	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_cases_report_outcome ~87

Report a real-world outcome for a decision case.

Input Output Examples

Name	Type	Req	Description
actual_impact	object	—	—
case_id	string	yes	—
correction_needed	boolean	—	—
description	string	—	—
details	object	—	—
revenue_impact	number	—	—
rollback_performed	boolean	—	—
status	string	yes	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_constraints_apply_patch ~81

Apply JSON Patch operations to a rule with preview/optimistic locking support.

Input Output Examples

Name	Type	Req	Description
idempotency_key	string	—	—
if_match	string	—	—
if_match_version	integer	—	—
patch	—	yes	—
preview	boolean	—	—
reason	string	—	—
rule_id	string	yes	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_constraints_create ~33

Create a boundary rule.

Input Output Examples

Name	Type	Req	Description
idempotency_key	string	—	—
payload	object	yes	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_constraints_delete ~33

Delete a rule.

Input Output Examples

Name	Type	Req	Description
idempotency_key	string	—	—
rule_id	string	yes	—

No output schema declared.

No examples provided.

bighub_constraints_domains ~16

List available rule domains.

Input Output Examples

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

bighub_constraints_dry_run ~29

Dry run a rule payload without persisting.

Input Output Examples

Name	Type	Req	Description
payload	object	yes	—

No output schema declared.

No examples provided.

bighub_constraints_get ~27

Fetch a single rule by rule_id.

Input Output Examples

Name	Type	Req	Description
rule_id	string	yes	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_constraints_list ~43

List boundary rules.

Input Output Examples

Name	Type	Req	Description
domain	string	—	—
limit	integer	—	—
offset	integer	—	—
status	string	—	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_constraints_pause ~36

Pause a rule by rule_id.

Input Output Examples

Name	Type	Req	Description
idempotency_key	string	—	—
rule_id	string	yes	—

No output schema declared.

No examples provided.

bighub_constraints_purge_idempotency ~52

Purge rule idempotency records from the backend store.

Input Output Examples

Name	Type	Req	Description
limit	integer	—	—
older_than_hours	integer	—	—
only_expired	boolean	—	—

Structured output declared, but exposes no named fields.

No examples provided.

bighub_constraints_resume ~34

Resume a paused rule.

Input Output Examples

Name	Type	Req	Description
idempotency_key	string	—	—
rule_id	string	yes	—

No output schema declared.

No examples provided.

On this page

Handy links

Scoring key

80+ high trust
60–79 medium
below 60 low

How we score

Score history · last 30 days

27 Jul 3 Aug

Day	Score
27 Jul	43
28 Jul	43
29 Jul	66
30 Jul	36
31 Jul	33
1 Aug	48
2 Aug	58
3 Aug	59