BIGHUB MCP server

Read from the package source without running it. The installed server may list more.

• bighub_actions_dashboard_summary

  Get action dashboard summary.

• bighub_actions_dry_runwrite action

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

• bighub_actions_evaluate

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

• bighub_actions_evaluate_payload

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

• bighub_actions_live_connect

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

• bighub_actions_live_disconnect

  Disconnect a live agent connection, freeing the slot immediately.

• bighub_actions_live_heartbeat

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

• bighub_actions_memory_context

  Read decision memory context window and rates.

• bighub_actions_memory_ingest

  Ingest scored execution events into decision memory.

• bighub_actions_memory_recommendations

  Compute decision memory recommendations.

• bighub_actions_memory_refresh_aggregates

  Refresh decision memory aggregates.

• bighub_actions_observer_stats

  Get action observer stats.

• bighub_actions_status

  Get action system status.

• bighub_actions_verify_validation

  Verify a previous evaluation by validation_id.

• bighub_api_keys_createwrite action

  Create an API key.

• bighub_api_keys_deletewrite action

  Delete or revoke an API key.

• bighub_api_keys_list

  List API keys.

• bighub_api_keys_rotate

  Rotate an API key.

• bighub_api_keys_scopes

  List available API key scopes.

• bighub_api_keys_validate

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

• bighub_approvals_list

  List approval queue items.

• bighub_approvals_resolve

  Resolve an approval request.

• bighub_auth_login

  Authenticate and return access/refresh tokens.

• bighub_auth_logout

  Invalidate a refresh token.

• bighub_auth_refresh

  Rotate auth tokens with refresh token.

• bighub_auth_signup

  Sign up and return access/refresh tokens.

• bighub_calibration_breakdown

  Calibration breakdown by dimension.

• bighub_calibration_drift

  Detect calibration drift over time.

• bighub_calibration_feedback

  Calibration feedback and improvement suggestions.

• bighub_calibration_observewrite action

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

• bighub_calibration_quality_history

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

• bighub_calibration_reliability

  Calibration reliability diagram data.

• bighub_calibration_report

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

• bighub_cases_calibration

  Get calibration metrics (prediction vs reality) for cases.

• bighub_cases_createwrite action

  Create a decision case. Requires action and verdict.

• bighub_cases_get

  Get a decision case by ID.

• bighub_cases_list

  List decision cases with filters.

• bighub_cases_precedents

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

• bighub_cases_report_outcome

  Report a real-world outcome for a decision case.

• bighub_constraints_apply_patchwrite action

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

• bighub_constraints_createwrite action

  Create a boundary rule.

• bighub_constraints_deletewrite action

  Delete a rule.

• bighub_constraints_domains

  List available rule domains.

• bighub_constraints_dry_runwrite action

  Dry run a rule payload without persisting.

• bighub_constraints_get

  Fetch a single rule by rule_id.

• bighub_constraints_list

  List boundary rules.

• bighub_constraints_pause

  Pause a rule by rule_id.

• bighub_constraints_purge_idempotency

  Purge rule idempotency records from the backend store.

• bighub_constraints_resume

  Resume a paused rule.

• bighub_constraints_updatewrite action

  Update a rule by rule_id.

• bighub_constraints_validate

  Validate a rule payload.

• bighub_constraints_validate_dry_runwrite action

  Dry-run validate a rule payload.

• bighub_constraints_versions

  List historical versions for a rule.

• bighub_events_list

  List event stream entries.

• bighub_events_stats

  Get aggregate event stats.

• bighub_features_compare

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

• bighub_features_compute

  Compute decision features for a case.

• bighub_features_compute_batch

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

• bighub_features_explain

  Explain computed features for a case.

• bighub_features_export

  Export all features for a case.

• bighub_features_get_snapshot

  Get a feature snapshot by ID.

• bighub_features_list_snapshots

  List feature snapshots.

• bighub_features_schema

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

• bighub_features_snapshotwrite action

  Create a versioned feature snapshot for a case.

• bighub_features_stats

  Get feature layer statistics.

• bighub_http_request

  Low-level passthrough for any BIGHUB API endpoint.

• bighub_kill_switch_activatewrite action

  Activate global/domain kill switch. Requires a reason.

• bighub_kill_switch_deactivatewrite action

  Deactivate kill switch by switch_id. Requires a reason.

• bighub_kill_switch_statuswrite action

  Read kill switch status.

• bighub_outcomes_analytics

  Outcome analytics summary.

• bighub_outcomes_get

  Get outcome by request_id.

• bighub_outcomes_get_by_case

  Get outcome by case_id.

• bighub_outcomes_get_by_validation

  Get outcome by validation_id.

• bighub_outcomes_partner_view

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

• bighub_outcomes_pending

  List decisions still awaiting outcome reports.

• bighub_outcomes_recommendation_quality

  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.

• bighub_outcomes_report

  Report a real-world outcome linked to a decision.

• bighub_outcomes_report_batch

  Batch report outcomes (max 100).

• bighub_outcomes_taxonomy

  Supported outcome status taxonomy.

• bighub_outcomes_timeline

  Get full outcome timeline for a request.

• bighub_precedents_query

  Query similar past decision cases.

• bighub_precedents_signals

  Get aggregated precedent signals for an action.

• bighub_precedents_stats

  Get precedent engine statistics.

• bighub_retrieval_compare

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

• bighub_retrieval_index_case

  Index a decision case into the retrieval engine.

• bighub_retrieval_query

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

• bighub_retrieval_query_explained

  Retrieval query with full scoring explanation.

• bighub_retrieval_stats

  Get retrieval engine statistics.

• bighub_retrieval_strategies

  List available retrieval strategies.

• bighub_retrieval_strategy

  Get details of a retrieval strategy by name.

• bighub_webhooks_createwrite action

  Create a webhook endpoint.

• bighub_webhooks_deletewrite action

  Delete a webhook.

• bighub_webhooks_deliveries

  List webhook delivery logs.

• bighub_webhooks_get

  Get a webhook by webhook_id.

• bighub_webhooks_list

  List webhooks.

• bighub_webhooks_list_events

  List supported webhook event types.

• bighub_webhooks_replay_failed_delivery

  Replay a failed webhook delivery.

• bighub_webhooks_testwrite action

  Send a test webhook delivery.

• bighub_webhooks_updatewrite action

  Update webhook by webhook_id.

• bighub_webhooks_verify_signature

  Verify webhook signature payload.

• Code scan4 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitystatic API keys via environment variables6/15
• Maintenancelast push 134 days ago8/15
• Maintainer identitynamespace and repository owner differ; website matches verified namespace6/10

Safety score

69/100

higher than 35% of 4,460 AI and agents servers

Tools

100

the typical AI and agents server has 6

Tools that change things

19%

typical: 0%. Fewer write tools means less an agent can break

BIGHUB: common questions

Is BIGHUB MCP server safe?

With care: it is graded C, so read the findings first (69/100). Read the BIGHUB safety report

How do I install BIGHUB?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does BIGHUB need an API key?

Yes. The registry entry asks for BIGHUB_API_KEY, BIGHUB_BEARER_TOKEN.

Is BIGHUB maintained?

The last commit was 172 days ago (2026-05-16). The latest release is v0.2.1.

What can I use instead of BIGHUB?

Servers from other publishers that do the same job: Mnemoverse Memory MCP server, Decionis MCP server and Agent-Native Chat MCP server.

How does BIGHUB compare with other AI and agents MCP servers?

safety score 69/100 (higher than 35% of 4,460 AI and agents servers); tools 100 (the typical AI and agents server has 6); tools that change things 19% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.