# BIGHUB (npm · @bighub/bighub-mcp)

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

- Trust score: 58/100 (low)
- Change this week: +15
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-04

## Components

- npm · `@bighub/bighub-mcp`: 58/100 (this document), [markdown](https://verifymcp.io/servers/io-bighub-mcp/bighub-bighub-mcp.md), [page](https://verifymcp.io/servers/io-bighub-mcp/bighub-bighub-mcp)

## Channel facts

- Registry: `npm`
- Package: `@bighub/bighub-mcp`
- Version: `0.2.1`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-04.

- **Supply Chain Security**: 83/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known medium-severity CVE affects hono 4.12.33, reached via @modelcontextprotocol/sdk > hono. A fixed version is available.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 132 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 37/100
  - AI-judged instruction clarity (poor).
  - Tool/resource definitions use about 5931 tokens (~47/item across 125 items; 125 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 75/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 11% of tool parameters carry a description.
  - Structured output schemas are declared (64% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

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

### Codex

```bash
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
    }
  }
}
```

### OpenClaw

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

### Hermes

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

### Other

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

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-04 (score 58, −1)

- [security regression] CVE-2026-69207 affects this package: medium
- [security regression] Known CVEs: partial → fail

### 2026-08-03 (score 59, +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.

### 2026-08-02 (score 58, +10)

- [security improvement] Known CVEs: unverified → partial
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] Dependency health: unverified → partial

### 2026-08-01 (score 48, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-07-31 (score 33, −3)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 36, −30)

- [security regression] Known CVEs: partial → unverified
- [security regression] Malware scan: pass → unverified
- [functional regression] Dependency health: partial → unverified

### 2026-07-29 (score 66, +23)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [functional improvement] Schema quality: unverified → poor
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] License: unverified → pass
- [functional] Licence: MIT

### 2026-07-27 (score 43)

First indexed and scored.

## MCP tools (125)

### `bighub_http_request` (~67 tokens)

Low-level passthrough for any BIGHUB API endpoint.

Input parameters:

- `body`
- `headers` (object)
- `idempotency_key` (string)
- `method` (string, required)
- `path` (string, required)
- `query` (object)

### `bighub_actions_evaluate` (~94 tokens)

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

Input parameters:

- `action` (string, required)
- `actor` (string)
- `context` (object)
- `domain` (string)
- `idempotency_key` (string)
- `metadata` (object)
- `target` (string)
- `value` (number)

### `bighub_actions_evaluate_payload` (~44 tokens)

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

Input parameters:

- `idempotency_key` (string)
- `payload` (object, required)

### `bighub_actions_dry_run` (~49 tokens)

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

Input parameters:

- `idempotency_key` (string)
- `payload` (object, required)

### `bighub_actions_live_connect` (~45 tokens)

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

Input parameters:

- `actor` (string)
- `context` (object)

### `bighub_actions_live_heartbeat` (~51 tokens)

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

Input parameters:

- `connection_id` (string, required)
- `context` (object)

### `bighub_actions_live_disconnect` (~38 tokens)

Disconnect a live agent connection, freeing the slot immediately.

Input parameters:

- `connection_id` (string, required)
- `context` (object)

### `bighub_actions_verify_validation` (~28 tokens)

Verify a previous evaluation by validation_id.

Input parameters:

- `validation_id` (string, required)

### `bighub_actions_observer_stats` (~18 tokens)

Get action observer stats.

### `bighub_actions_dashboard_summary` (~17 tokens)

Get action dashboard summary.

### `bighub_actions_status` (~16 tokens)

Get action system status.

### `bighub_actions_memory_ingest` (~89 tokens)

Ingest scored execution events into decision memory.

Input parameters:

- `actor` (string)
- `domain` (string)
- `events` (array, required)
- `model` (string)
- `redact` (boolean)
- `redaction_policy` (string)
- `source` (string)
- `source_version` (string)
- `trace_id` (string)

### `bighub_actions_memory_context` (~64 tokens)

Read decision memory context window and rates.

Input parameters:

- `actor` (string)
- `domain` (string)
- `limit_recent` (integer)
- `source` (string)
- `tool` (string)
- `window_hours` (integer)

### `bighub_actions_memory_refresh_aggregates` (~35 tokens)

Refresh decision memory aggregates.

Input parameters:

- `concurrent` (boolean)
- `window_hours` (integer)

### `bighub_actions_memory_recommendations` (~126 tokens)

Compute decision memory recommendations.

Input parameters:

- `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)

### `bighub_constraints_create` (~33 tokens)

Create a boundary rule.

Input parameters:

- `idempotency_key` (string)
- `payload` (object, required)

### `bighub_constraints_list` (~43 tokens)

List boundary rules.

Input parameters:

- `domain` (string)
- `limit` (integer)
- `offset` (integer)
- `status` (string)

### `bighub_constraints_get` (~27 tokens)

Fetch a single rule by rule_id.

Input parameters:

- `rule_id` (string, required)

### `bighub_constraints_update` (~43 tokens)

Update a rule by rule_id.

Input parameters:

- `idempotency_key` (string)
- `payload` (object, required)
- `rule_id` (string, required)

### `bighub_constraints_delete` (~33 tokens)

Delete a rule.

Input parameters:

- `idempotency_key` (string)
- `rule_id` (string, required)

### `bighub_constraints_pause` (~36 tokens)

Pause a rule by rule_id.

Input parameters:

- `idempotency_key` (string)
- `rule_id` (string, required)

### `bighub_constraints_resume` (~34 tokens)

Resume a paused rule.

Input parameters:

- `idempotency_key` (string)
- `rule_id` (string, required)

### `bighub_constraints_dry_run` (~29 tokens)

Dry run a rule payload without persisting.

Input parameters:

- `payload` (object, required)

### `bighub_constraints_validate` (~23 tokens)

Validate a rule payload.

Input parameters:

- `payload` (object, required)

### `bighub_constraints_validate_dry_run` (~28 tokens)

Dry-run validate a rule payload.

Input parameters:

- `payload` (object, required)

### `bighub_constraints_domains` (~16 tokens)

List available rule domains.

### `bighub_constraints_versions` (~33 tokens)

List historical versions for a rule.

Input parameters:

- `limit` (integer)
- `rule_id` (string, required)

### `bighub_constraints_purge_idempotency` (~52 tokens)

Purge rule idempotency records from the backend store.

Input parameters:

- `limit` (integer)
- `older_than_hours` (integer)
- `only_expired` (boolean)

### `bighub_constraints_apply_patch` (~81 tokens)

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

Input parameters:

- `idempotency_key` (string)
- `if_match` (string)
- `if_match_version` (integer)
- `patch` (required)
- `preview` (boolean)
- `reason` (string)
- `rule_id` (string, required)

### `bighub_approvals_list` (~33 tokens)

List approval queue items.

Input parameters:

- `limit` (integer)
- `status_filter` (string)

### `bighub_approvals_resolve` (~41 tokens)

Resolve an approval request.

Input parameters:

- `comment` (string)
- `request_id` (string, required)
- `resolution` (string, required)

### `bighub_kill_switch_status` (~18 tokens)

Read kill switch status.

### `bighub_kill_switch_activate` (~76 tokens)

Activate global/domain kill switch. Requires a reason.

Input parameters:

- `domain` (string): Domain to target (when scope=domain)
- `reason` (string, required): Why the kill switch is being activated
- `rule_id` (string): Specific rule to kill
- `scope` (string): Scope: global or domain

### `bighub_kill_switch_deactivate` (~71 tokens)

Deactivate kill switch by switch_id. Requires a reason.

Input parameters:

- `domain` (string)
- `reason` (string, required): Why the kill switch is being deactivated
- `rule_id` (string)
- `scope` (string)
- `switch_id` (string, required)

### `bighub_events_list` (~53 tokens)

List event stream entries.

Input parameters:

- `event_type` (string)
- `limit` (integer)
- `offset` (integer)
- `rule_id` (string)
- `severity` (string)

### `bighub_events_stats` (~16 tokens)

Get aggregate event stats.

### `bighub_api_keys_create` (~24 tokens)

Create an API key.

Input parameters:

- `payload` (object, required)

### `bighub_api_keys_list` (~25 tokens)

List API keys.

Input parameters:

- `include_revoked` (boolean)

### `bighub_api_keys_delete` (~34 tokens)

Delete or revoke an API key.

Input parameters:

- `key_id` (string, required)
- `reason` (string)

### `bighub_api_keys_rotate` (~25 tokens)

Rotate an API key.

Input parameters:

- `key_id` (string, required)

### `bighub_api_keys_validate` (~33 tokens)

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

Input parameters:

- `api_key` (string, required)

### `bighub_api_keys_scopes` (~19 tokens)

List available API key scopes.

### `bighub_webhooks_create` (~24 tokens)

Create a webhook endpoint.

Input parameters:

- `payload` (object, required)

### `bighub_webhooks_list` (~25 tokens)

List webhooks.

Input parameters:

- `include_inactive` (boolean)

### `bighub_webhooks_get` (~27 tokens)

Get a webhook by webhook_id.

Input parameters:

- `webhook_id` (string, required)

### `bighub_webhooks_update` (~33 tokens)

Update webhook by webhook_id.

Input parameters:

- `payload` (object, required)
- `webhook_id` (string, required)

### `bighub_webhooks_delete` (~24 tokens)

Delete a webhook.

Input parameters:

- `webhook_id` (string, required)

### `bighub_webhooks_deliveries` (~34 tokens)

List webhook delivery logs.

Input parameters:

- `limit` (integer)
- `webhook_id` (string, required)

### `bighub_webhooks_test` (~34 tokens)

Send a test webhook delivery.

Input parameters:

- `event_type` (string)
- `webhook_id` (string, required)

### `bighub_webhooks_list_events` (~19 tokens)

List supported webhook event types.

### `bighub_webhooks_verify_signature` (~46 tokens)

Verify webhook signature payload.

Input parameters:

- `payload` (string, required)
- `secret` (string, required)
- `signature` (string, required)
- `timestamp` (integer, required)

### `bighub_webhooks_replay_failed_delivery` (~37 tokens)

Replay a failed webhook delivery.

Input parameters:

- `delivery_id` (integer, required)
- `webhook_id` (string, required)

### `bighub_auth_signup` (~27 tokens)

Sign up and return access/refresh tokens.

Input parameters:

- `payload` (object, required)

### `bighub_auth_login` (~26 tokens)

Authenticate and return access/refresh tokens.

Input parameters:

- `payload` (object, required)

### `bighub_auth_refresh` (~26 tokens)

Rotate auth tokens with refresh token.

Input parameters:

- `refresh_token` (string)

### `bighub_auth_logout` (~25 tokens)

Invalidate a refresh token.

Input parameters:

- `refresh_token` (string)

### `bighub_cases_create` (~158 tokens)

Create a decision case. Requires action and verdict.

Input parameters:

- `action` (object, required): Action payload: {tool, action, arguments, value, target, domain}
- `actor_id` (string)
- `actor_type` (string)
- `agent_model` (string)
- `context` (object)
- `domain` (string, required)
- `goal_summary` (string)
- `refs` (object)
- `simulation` (object)
- `tags` (array)
- `trigger_source` (string)
- `verdict` (object, required): Required verdict: {verdict: ALLOWED|BLOCKED|APPROVAL_REQUIRED|LIMITED|DRY_RUN, mode, reasons, risk_score, confidence}

### `bighub_cases_get` (~26 tokens)

Get a decision case by ID.

Input parameters:

- `case_id` (string, required)

### `bighub_cases_list` (~96 tokens)

List decision cases with filters.

Input parameters:

- `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)

### `bighub_cases_report_outcome` (~87 tokens)

Report a real-world outcome for a decision case.

Input parameters:

- `actual_impact` (object)
- `case_id` (string, required)
- `correction_needed` (boolean)
- `description` (string)
- `details` (object)
- `revenue_impact` (number)
- `rollback_performed` (boolean)
- `status` (string, required)

### `bighub_cases_precedents` (~103 tokens)

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

Input parameters:

- `action` (object, required): 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)

### `bighub_cases_calibration` (~30 tokens)

Get calibration metrics (prediction vs reality) for cases.

Input parameters:

- `domain` (string)

### `bighub_outcomes_report` (~182 tokens)

Report a real-world outcome linked to a decision.

Input parameters:

- `actual_impact` (object)
- `case_id` (string)
- `correction_cost` (number)
- `correction_description` (string)
- `correction_needed` (boolean)
- `customer_impact_count` (integer)
- `description` (string)
- `details` (object)
- `observed_at` (string)
- `reported_by` (string)
- `request_id` (string)
- `revenue_impact` (number)
- `rollback_performed` (boolean)
- `status` (string, required)
- `support_tickets_created` (integer)
- `tags` (array)
- `time_to_detect_s` (number)
- `time_to_resolve_s` (number)
- `validation_id` (string)

### `bighub_outcomes_report_batch` (~28 tokens)

Batch report outcomes (max 100).

Input parameters:

- `outcomes` (array, required)

### `bighub_outcomes_get` (~26 tokens)

Get outcome by request_id.

Input parameters:

- `request_id` (string, required)

### `bighub_outcomes_get_by_validation` (~28 tokens)

Get outcome by validation_id.

Input parameters:

- `validation_id` (string, required)

### `bighub_outcomes_get_by_case` (~28 tokens)

Get outcome by case_id.

Input parameters:

- `case_id` (string, required)

### `bighub_outcomes_timeline` (~29 tokens)

Get full outcome timeline for a request.

Input parameters:

- `request_id` (string, required)

### `bighub_outcomes_pending` (~35 tokens)

List decisions still awaiting outcome reports.

Input parameters:

- `limit` (integer)
- `min_age_hours` (integer)

### `bighub_outcomes_analytics` (~38 tokens)

Outcome analytics summary.

Input parameters:

- `domain` (string)
- `since` (string)
- `until` (string)

### `bighub_outcomes_taxonomy` (~18 tokens)

Supported outcome status taxonomy.

### `bighub_outcomes_recommendation_quality` (~98 tokens)

Recommendation quality analytics: follow rate, quadrants (followed+positive, followed+negative, ignored+positive, ignored+negative), breakdowns by domain/actor, and notable examples of BIGHUB helped / missed.

Input parameters:

- `domain` (string): Filter by domain
- `since` (string): Start date (ISO 8601)
- `until` (string): End date (ISO 8601)

### `bighub_outcomes_partner_view` (~60 tokens)

Self-contained partner/domain view: decisions evaluated, follow rate, positive after following, trend, by-action breakdown, sparse evidence pockets, and helped/missed examples.

Input parameters:

- `domain` (string, required): The domain to generate the partner view for

### `bighub_precedents_query` (~95 tokens)

Query similar past decision cases.

Input parameters:

- `action` (string, required)
- `actor_type` (string)
- `axes` (object)
- `domain` (string, required)
- `intent` (string)
- `max_results` (integer)
- `min_similarity` (number)
- `require_outcome` (boolean)
- `risk_score` (number)
- `tool` (string)

### `bighub_precedents_signals` (~66 tokens)

Get aggregated precedent signals for an action.

Input parameters:

- `action` (string, required)
- `actor_type` (string)
- `axes` (object)
- `domain` (string, required)
- `risk_score` (number)
- `tool` (string)

### `bighub_precedents_stats` (~18 tokens)

Get precedent engine statistics.

### `bighub_calibration_report` (~47 tokens)

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

Input parameters:

- `domain` (string)
- `risk_band` (string)
- `tool` (string)

### `bighub_calibration_reliability` (~33 tokens)

Calibration reliability diagram data.

Input parameters:

- `domain` (string)
- `tool` (string)

### `bighub_calibration_drift` (~34 tokens)

Detect calibration drift over time.

Input parameters:

- `domain` (string)
- `window_days` (integer)

### `bighub_calibration_breakdown` (~25 tokens)

Calibration breakdown by dimension.

Input parameters:

- `by` (string)

### `bighub_calibration_feedback` (~25 tokens)

Calibration feedback and improvement suggestions.

Input parameters:

- `domain` (string)

### `bighub_calibration_observe` (~86 tokens)

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

Input parameters:

- `action` (string)
- `actor_type` (string)
- `case_id` (string, required)
- `domain` (string)
- `outcome_status` (string, required)
- `predicted_risk` (number, required)
- `tool` (string)
- `verdict` (string)

### `bighub_calibration_quality_history` (~57 tokens)

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

Input parameters:

- `days` (integer): Number of days to include
- `domain` (string)

### `bighub_retrieval_query` (~87 tokens)

Multi-signal decision retrieval: find relevant past cases for an upcoming action.

Input parameters:

- `action` (string, required)
- `actor_type` (string)
- `axes` (object)
- `domain` (string, required)
- `risk_score` (number)
- `strategy` (string)
- `strategy_name` (string)
- `tool` (string)

### `bighub_retrieval_query_explained` (~82 tokens)

Retrieval query with full scoring explanation.

Input parameters:

- `action` (string, required)
- `actor_type` (string)
- `axes` (object)
- `domain` (string, required)
- `risk_score` (number)
- `strategy` (string)
- `strategy_name` (string)
- `tool` (string)

### `bighub_retrieval_strategies` (~20 tokens)

List available retrieval strategies.

### `bighub_retrieval_strategy` (~29 tokens)

Get details of a retrieval strategy by name.

Input parameters:

- `name` (string, required)

### `bighub_retrieval_index_case` (~90 tokens)

Index a decision case into the retrieval engine.

Input parameters:

- `action` (string, required)
- `actor_type` (string)
- `axes` (object)
- `case_id` (string, required)
- `domain` (string, required)
- `org_id` (string, required)
- `risk_score` (number)
- `tool` (string, required)
- `verdict` (string)

### `bighub_retrieval_stats` (~18 tokens)

Get retrieval engine statistics.

### `bighub_retrieval_compare` (~120 tokens)

Compare two retrieval strategies on the same query. Returns scored results, risk level, confidence, and stability for each strategy.

Input parameters:

- `action` (string)
- `actor_type` (string)
- `axes` (object): Risk axes as {axis_name: score}
- `domain` (string)
- `intent` (string)
- `risk_score` (number)
- `strategy_a` (string): First strategy to compare
- `strategy_b` (string): Second strategy to compare
- `tool` (string)

### `bighub_features_compute` (~58 tokens)

Compute decision features for a case.

Input parameters:

- `advisory_data` (object)
- `case_data` (object, required)
- `case_id` (string, required)
- `org_id` (string, required)
- `precedent_data` (object)

### `bighub_features_snapshot` (~36 tokens)

Create a versioned feature snapshot for a case.

Input parameters:

- `case_id` (string, required)
- `tag` (string)

### `bighub_features_get_snapshot` (~27 tokens)

Get a feature snapshot by ID.

Input parameters:

- `snapshot_id` (string, required)

### `bighub_features_list_snapshots` (~32 tokens)

List feature snapshots.

Input parameters:

- `case_id` (string)
- `tag` (string)

### `bighub_features_explain` (~35 tokens)

Explain computed features for a case.

Input parameters:

- `case_id` (string, required)
- `feature_key` (string)

### `bighub_features_export` (~26 tokens)

Export all features for a case.

Input parameters:

- `case_id` (string, required)

### `bighub_features_schema` (~22 tokens)

Get the feature schema (all defined features and types).

### `bighub_features_stats` (~16 tokens)

Get feature layer statistics.

### `bighub_features_compute_batch` (~34 tokens)

Compute feature vectors for multiple cases in a single request (max 500).

Input parameters:

- `cases` (array, required)

### `bighub_features_compare` (~75 tokens)

Compare two feature snapshots or cached vectors. Returns changed features with diffs.

Input parameters:

- `case_id_a` (string)
- `case_id_b` (string)
- `changed_only` (boolean): Only return features that differ
- `snapshot_id_a` (string)
- `snapshot_id_b` (string)

### `bighub_features_export_batch` (~33 tokens)

Export flat feature dicts for multiple cases (max 500).

Input parameters:

- `case_ids` (array, required)

### `bighub_insights_advise` (~62 tokens)

Get decision advisory for a proposed action based on learned patterns.

Input parameters:

- `action` (string, required)
- `actor_type` (string)
- `domain` (string, required)
- `risk_band` (string)
- `tool` (string, required)

### `bighub_insights_patterns` (~48 tokens)

List detected decision patterns.

Input parameters:

- `domain` (string)
- `min_severity` (string)
- `pattern_type` (string)
- `tool` (string)

### `bighub_insights_learn` (~20 tokens)

Trigger pattern learning from accumulated cases.

### `bighub_insights_profile` (~43 tokens)

Get action quality profile for a tool/action/domain.

Input parameters:

- `action` (string)
- `domain` (string)
- `tool` (string)

### `bighub_simulations_list` (~47 tokens)

List persisted simulation snapshots.

Input parameters:

- `domain` (string)
- `limit` (integer)
- `tool` (string)
- `with_outcome` (boolean)

### `bighub_simulations_get` (~27 tokens)

Get a simulation snapshot by ID.

Input parameters:

- `snapshot_id` (string, required)

### `bighub_simulations_by_request` (~30 tokens)

Get simulation snapshot for a given request_id.

Input parameters:

- `request_id` (string, required)

### `bighub_simulations_compare` (~30 tokens)

Compare simulation prediction vs real outcome for a request.

Input parameters:

- `request_id` (string, required)

### `bighub_simulations_accuracy` (~30 tokens)

Simulation accuracy metrics.

Input parameters:

- `domain` (string)
- `tool` (string)

### `bighub_simulations_stats` (~17 tokens)

Get simulation vault statistics.

### `bighub_learning_strategy` (~19 tokens)

Get current learning strategy version and configuration.

### `bighub_learning_runs` (~24 tokens)

List recent learning pipeline runs.

Input parameters:

- `limit` (integer)

### `bighub_learning_recompute` (~59 tokens)

Trigger recomputation of learning artifacts for a scope.

Input parameters:

- `action_family` (string)
- `async_mode` (boolean)
- `domain` (string)
- `force` (boolean)
- `limit` (integer)

### `bighub_learning_backfill` (~57 tokens)

Backfill learning artifacts from historical outcomes.

Input parameters:

- `action_family` (string)
- `async_mode` (boolean)
- `domain` (string)
- `force` (boolean)
- `limit` (integer)

### `bighub_actions_evaluate_batch` (~71 tokens)

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 parameters:

- `actions` (array, required)
- `idempotency_key` (string)

### `bighub_ingest_event` (~398 tokens)

Ingest a single real-world event into BIGHUB. Events flow through: normalize → enrich → correlate → sync. BIGHUB links the event to the correct decision lifecycle using any provided correlation key.

Input parameters:

- `action` (object): Action payload: {tool, action, arguments, value, target, domain}
- `adapter` (string)
- `case_id` (string): Link to DecisionCase
- `context` (object): Context: {risk_score, axes, environment, ...}
- `domain` (string)
- `entity_id` (string): Entity being acted on
- `event_type` (string): Event type: ACTION_PROPOSED, ACTION_EXECUTED, ACTION_BLOCKED, HUMAN_OVERRIDE, HUMAN_APPROVAL, HUMAN_REJECTION, OUTCOME_OBSERVED, OUTCOME_UPDATED, ROLLBACK_PERFORMED, CORRECTION_APPLIED, ESCALATION_TR…
- `execution` (object): Execution result: {executed, status_code, error, ...}
- `external_ref` (string): Your system's reference (e.g. order_id)
- `human_feedback` (object): Human: {feedback_type, decision, reason, ...}
- `intent` (object): Intent: {goal_summary, trigger_source, actor_type, ...}
- `outcome` (object): Outcome: {status, description, revenue_impact, ...}
- `request_id` (string): Link to BIGHUB decision (from /actions/evaluate response)
- `session_id` (string): Session / conversation ID
- `tags` (array)
- `tenant_ref` (string): Tenant-level reference
- `timestamp` (string): ISO 8601 timestamp (defaults to now)
- `validation_id` (string): Link to rule validation

### `bighub_ingest_batch` (~67 tokens)

Ingest multiple real-world events in a single request (max 500). Events are processed through the same normalize → enrich → correlate → sync pipeline.

Input parameters:

- `adapter` (string)
- `domain` (string)
- `events` (array, required): Raw event payloads

### `bighub_ingest_reconcile` (~91 tokens)

Reconcile a late-arriving outcome with a previous decision. Use when the outcome arrives after the initial event was already ingested.

Input parameters:

- `key_name` (string, required): Correlation key: request_id, case_id, external_ref, tenant_ref, or entity_id
- `key_value` (string, required): Value of the correlation key
- `outcome` (object, required): Outcome event payload to attach

### `bighub_ingest_lifecycles` (~44 tokens)

List decision lifecycles with optional status filter.

Input parameters:

- `limit` (integer)
- `status_filter` (string): Filter by lifecycle status

### `bighub_ingest_lifecycle` (~62 tokens)

Get a specific decision lifecycle by correlation key.

Input parameters:

- `case_id` (string)
- `entity_id` (string)
- `external_ref` (string)
- `request_id` (string)
- `tenant_ref` (string)

### `bighub_ingest_pending` (~27 tokens)

List lifecycles awaiting outcome reconciliation.

Input parameters:

- `limit` (integer)

### `bighub_ingest_stale` (~45 tokens)

List stale lifecycles that have not received an outcome within the expected timeframe.

Input parameters:

- `limit` (integer)
- `stale_after_days` (integer)

### `bighub_ingest_stats` (~28 tokens)

Get organization-wide ingestion statistics (event counts, adapter breakdown, lifecycle status distribution).

### `bighub_ingest_adapters` (~22 tokens)

List available ingestion adapters and domain normalizers.

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/io-bighub-mcp/bighub-bighub-mcp#diagnostics

## Score history

- 2026-08-04: 58
- 2026-08-03: 59
- 2026-08-02: 58
- 2026-08-01: 48
- 2026-07-31: 33
- 2026-07-30: 36
- 2026-07-29: 66
- 2026-07-28: 43
- 2026-07-27: 43

## Links

- npm package: https://www.npmjs.com/package/@bighub/bighub-mcp
- Socket report: https://socket.dev/npm/package/@bighub/bighub-mcp
- Repository: https://github.com/bighub-io/bighub
- Website: https://bighub.io/
- Changelog RSS feed: https://verifymcp.io/servers/io-bighub-mcp/bighub-bighub-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-bighub-mcp/bighub-bighub-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/io-bighub-mcp/bighub-bighub-mcp