// MCP TOOL REFERENCE

BIGHUB TOOLS

125 tools from the BIGHUB MCP Server, categorised by risk level.

View the BIGHUB policy → Token cost: 11,747 tokens →
// ALL 125 BIGHUB TOOLS
READ 100 tools
Read bighub_actions_dashboard_summary Get action dashboard summary. Read bighub_actions_evaluate Evaluate an action via /actions/evaluate — returns decision intelligence (recommendation, risk, trajectory ... Read bighub_actions_evaluate_batch Evaluate multiple actions in a single request via /actions/evaluate/batch. Each element follows the same sc... Read bighub_actions_evaluate_payload Evaluate an action with full decision intelligence payload via /actions/evaluate. Read bighub_actions_live_heartbeat Heartbeat an existing live agent connection to keep it alive (recommended every 40s, TTL 120s). Read bighub_actions_memory_context Read decision memory context window and rates. Read bighub_actions_memory_ingest Ingest scored execution events into decision memory. Read bighub_actions_memory_recommendations Compute decision memory recommendations. Read bighub_actions_memory_refresh_aggregates Refresh decision memory aggregates. Read bighub_actions_observer_stats Get action observer stats. Read bighub_actions_status Get action system status. Read bighub_actions_verify_validation Verify a previous evaluation by validation_id. Read bighub_api_keys_list List API keys. Read bighub_api_keys_rotate Rotate an API key. Read bighub_api_keys_scopes List available API key scopes. Read bighub_api_keys_validate Validate an API key (query + X-API-Key header). Read bighub_approvals_list List approval queue items. Read bighub_auth_logout Invalidate a refresh token. Read bighub_auth_refresh Rotate auth tokens with refresh token. Read bighub_auth_signup Sign up and return access/refresh tokens. Read bighub_calibration_breakdown Calibration breakdown by dimension. Read bighub_calibration_drift Detect calibration drift over time. Read bighub_calibration_feedback Calibration feedback and improvement suggestions. Read bighub_calibration_observe Submit a calibration observation (predicted risk vs real outcome). Read bighub_calibration_quality_history Daily quality score over time — powers the Learning chart. Returns quality_score (1 − Brier), positive_rate... Read bighub_calibration_reliability Calibration reliability diagram data. Read bighub_calibration_report Calibration report: how well do predicted risk scores match real outcomes. Read bighub_cases_calibration Get calibration metrics (prediction vs reality) for cases. Read bighub_cases_get Get a decision case by ID. Read bighub_cases_list List decision cases with filters. Read bighub_cases_precedents Get precedent intelligence for a proposed action. action must be a nested ActionInput object. Read bighub_cases_report_outcome Report a real-world outcome for a decision case. Read bighub_constraints_domains List available rule domains. Read bighub_constraints_get Fetch a single rule by rule_id. Read bighub_constraints_list List boundary rules. Read bighub_constraints_pause Pause a rule by rule_id. Read bighub_constraints_validate Validate a rule payload. Read bighub_constraints_validate_dry_run Dry-run validate a rule payload. Read bighub_constraints_versions List historical versions for a rule. Read bighub_events_list List event stream entries. Read bighub_events_stats Get aggregate event stats. Read bighub_features_compare Compare two feature snapshots or cached vectors. Returns changed features with diffs. Read bighub_features_compute Compute decision features for a case. Read bighub_features_compute_batch Compute feature vectors for multiple cases in a single request (max 500). Read bighub_features_explain Explain computed features for a case. Read bighub_features_get_snapshot Get a feature snapshot by ID. Read bighub_features_list_snapshots List feature snapshots. Read bighub_features_schema Get the feature schema (all defined features and types). Read bighub_features_snapshot Create a versioned feature snapshot for a case. Read bighub_features_stats Get feature layer statistics. Read bighub_http_request Low-level passthrough for any BIGHUB API endpoint. Read bighub_ingest_adapters List available ingestion adapters and domain normalizers. Read bighub_ingest_batch Ingest multiple real-world events in a single request (max 500). Events are processed through the same norm... Read bighub_ingest_event Ingest a single real-world event into BIGHUB. Events flow through: normalize → enrich → correlate → sync. B... Read bighub_ingest_lifecycle Get a specific decision lifecycle by correlation key. Read bighub_ingest_lifecycles List decision lifecycles with optional status filter. Read bighub_ingest_pending List lifecycles awaiting outcome reconciliation. Read bighub_ingest_reconcile Reconcile a late-arriving outcome with a previous decision. Use when the outcome arrives after the initial ... Read bighub_ingest_stale List stale lifecycles that have not received an outcome within the expected timeframe. Read bighub_ingest_stats Get organization-wide ingestion statistics (event counts, adapter breakdown, lifecycle status distribution). Read bighub_insights_advise Get decision advisory for a proposed action based on learned patterns. Read bighub_insights_patterns List detected decision patterns. Read bighub_insights_profile Get action quality profile for a tool/action/domain. Read bighub_learning_backfill Backfill learning artifacts from historical outcomes. Read bighub_learning_runs List recent learning pipeline runs. Read bighub_learning_strategy Get current learning strategy version and configuration. Read bighub_outcomes_analytics Outcome analytics summary. Read bighub_outcomes_get Get outcome by request_id. Read bighub_outcomes_get_by_case Get outcome by case_id. Read bighub_outcomes_get_by_validation Get outcome by validation_id. Read bighub_outcomes_partner_view Self-contained partner/domain view: decisions evaluated, follow rate, positive after following, trend, by-a... Read bighub_outcomes_pending List decisions still awaiting outcome reports. Read bighub_outcomes_recommendation_quality Recommendation quality analytics: follow rate, quadrants (followed+positive, followed+negative, ignored+pos... Read bighub_outcomes_report Report a real-world outcome linked to a decision. Read bighub_outcomes_report_batch Batch report outcomes (max 100). Read bighub_outcomes_taxonomy Supported outcome status taxonomy. Read bighub_outcomes_timeline Get full outcome timeline for a request. Read bighub_precedents_query Query similar past decision cases. Read bighub_precedents_signals Get aggregated precedent signals for an action. Read bighub_precedents_stats Get precedent engine statistics. Read bighub_retrieval_compare Compare two retrieval strategies on the same query. Returns scored results, risk level, confidence, and sta... Read bighub_retrieval_index_case Index a decision case into the retrieval engine. Read bighub_retrieval_query Multi-signal decision retrieval: find relevant past cases for an upcoming action. Read bighub_retrieval_query_explained Retrieval query with full scoring explanation. Read bighub_retrieval_stats Get retrieval engine statistics. Read bighub_retrieval_strategies List available retrieval strategies. Read bighub_retrieval_strategy Get details of a retrieval strategy by name. Read bighub_simulations_accuracy Simulation accuracy metrics. Read bighub_simulations_by_request Get simulation snapshot for a given request_id. Read bighub_simulations_compare Compare simulation prediction vs real outcome for a request. Read bighub_simulations_get Get a simulation snapshot by ID. Read bighub_simulations_list List persisted simulation snapshots. Read bighub_simulations_stats Get simulation vault statistics. Read bighub_webhooks_deliveries List webhook delivery logs. Read bighub_webhooks_get Get a webhook by webhook_id. Read bighub_webhooks_list List webhooks. Read bighub_webhooks_list_events List supported webhook event types. Read bighub_webhooks_replay_failed_delivery Replay a failed webhook delivery. Read bighub_webhooks_test Send a test webhook delivery. Read bighub_webhooks_verify_signature Verify webhook signature payload.
WRITE 17 tools
Write bighub_actions_live_connect Open a concurrent live agent connection slot. Returns connection_id to reuse for heartbeats and submits. Write bighub_actions_live_disconnect Disconnect a live agent connection, freeing the slot immediately. Write bighub_api_keys_create Create an API key. Write bighub_approvals_resolve Resolve an approval request. Write bighub_auth_login Authenticate and return access/refresh tokens. Write bighub_cases_create Create a decision case. Requires action and verdict. Write bighub_constraints_apply_patch Apply JSON Patch operations to a rule with preview/optimistic locking support. Write bighub_constraints_create Create a boundary rule. Write bighub_constraints_resume Resume a paused rule. Write bighub_constraints_update Update a rule by rule_id. Write bighub_features_export Export all features for a case. Write bighub_features_export_batch Export flat feature dicts for multiple cases (max 500). Write bighub_kill_switch_activate Activate global/domain kill switch. Requires a reason. Write bighub_kill_switch_deactivate Deactivate kill switch by switch_id. Requires a reason. Write bighub_kill_switch_status Read kill switch status. Write bighub_webhooks_create Create a webhook endpoint. Write bighub_webhooks_update Update webhook by webhook_id.
DESTRUCTIVE 4 tools
Destructive bighub_api_keys_delete Delete or revoke an API key. Destructive bighub_constraints_delete Delete a rule. Destructive bighub_constraints_purge_idempotency Purge rule idempotency records from the backend store. Destructive bighub_webhooks_delete Delete a webhook.
EXECUTE 4 tools
Execute bighub_actions_dry_run Dry-run action evaluation (non-persistent) via /actions/evaluate with dry_run=true. Execute bighub_constraints_dry_run Dry run a rule payload without persisting. Execute bighub_insights_learn Trigger pattern learning from accumulated cases. Execute bighub_learning_recompute Trigger recomputation of learning artifacts for a scope.
// RUNNING THIS SERVER

The managed route: connect BIGHUB through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y @bighub/bighub-mcp
// FAQ
How many tools does the BIGHUB MCP server have? +

The BIGHUB MCP server exposes 125 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on BIGHUB tools? +

Route the BIGHUB server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do BIGHUB tools fall into? +

BIGHUB tools are categorised as Read (100), Write (17), Destructive (4), Execute (4). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.