// SCAN REPORT

BIGHUB

125 tools. 25 can modify or destroy data without limits.

4 destructive tools with no built-in limits. Policy required.

Last updated: 3 Apr 2026

25 can modify or destroy data

100 read-only

125 tools total

// TOOL MAP

Read (100) Write / Execute (21) Destructive / Financial (4)

// WHAT CAN GO WRONG

Destructive tools (bighub_api_keys_delete, bighub_constraints_delete, bighub_constraints_purge_idempotency) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.

Write operations (bighub_actions_live_connect, bighub_actions_live_disconnect, bighub_api_keys_create) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.

Execute tools (bighub_actions_dry_run, bighub_constraints_dry_run, bighub_insights_learn) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.

One command. Full control.

Intercept sits between your agent and BIGHUB. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.

npx -y @policylayer/intercept scan -- npx -y @bighub/bighub-mcp

Scans every tool. Generates a policy. Starts enforcing.

Works with Claude Code · Cursor · Claude Desktop · Windsurf · any MCP client

// RECOMMENDED RULES

Deny destructive operations

bighub_api_keys_delete:
  rules:
    - action: deny

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

bighub_actions_live_connect:
  rules:
    - rate_limit: 30/hour

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

bighub_actions_dashboard_summary:
  rules:
    - rate_limit: 60/minute

Controls API costs and prevents retry loops from exhausting upstream rate limits.

// ALL 125 BIGHUB TOOLS

DESTRUCTIVE 4 tools

Destructive bighub_api_keys_delete Destructive bighub_constraints_delete Destructive bighub_constraints_purge_idempotency Destructive bighub_webhooks_delete

EXECUTE 4 tools

Execute bighub_actions_dry_run Execute bighub_constraints_dry_run Execute bighub_insights_learn Execute bighub_learning_recompute

WRITE 17 tools

Write bighub_actions_live_connect Write bighub_actions_live_disconnect Write bighub_api_keys_create Write bighub_approvals_resolve Write bighub_auth_login Write bighub_cases_create Write bighub_constraints_apply_patch Write bighub_constraints_create Write bighub_constraints_resume Write bighub_constraints_update Write bighub_features_export Write bighub_features_export_batch Write bighub_kill_switch_activate Write bighub_kill_switch_deactivate Write bighub_kill_switch_status Write bighub_webhooks_create Write bighub_webhooks_update

READ 100 tools

Read bighub_actions_dashboard_summary Read bighub_actions_evaluate Read bighub_actions_evaluate_batch Read bighub_actions_evaluate_payload Read bighub_actions_live_heartbeat Read bighub_actions_memory_context Read bighub_actions_memory_ingest Read bighub_actions_memory_recommendations Read bighub_actions_memory_refresh_aggregates Read bighub_actions_observer_stats Read bighub_actions_status Read bighub_actions_verify_validation Read bighub_api_keys_list Read bighub_api_keys_rotate Read bighub_api_keys_scopes Read bighub_api_keys_validate Read bighub_approvals_list Read bighub_auth_logout Read bighub_auth_refresh Read bighub_auth_signup Read bighub_calibration_breakdown Read bighub_calibration_drift Read bighub_calibration_feedback Read bighub_calibration_observe Read bighub_calibration_quality_history Read bighub_calibration_reliability Read bighub_calibration_report Read bighub_cases_calibration Read bighub_cases_get Read bighub_cases_list Read bighub_cases_precedents Read bighub_cases_report_outcome Read bighub_constraints_domains Read bighub_constraints_get Read bighub_constraints_list Read bighub_constraints_pause Read bighub_constraints_validate Read bighub_constraints_validate_dry_run Read bighub_constraints_versions Read bighub_events_list Read bighub_events_stats Read bighub_features_compare Read bighub_features_compute Read bighub_features_compute_batch Read bighub_features_explain Read bighub_features_get_snapshot Read bighub_features_list_snapshots Read bighub_features_schema Read bighub_features_snapshot Read bighub_features_stats Read bighub_http_request Read bighub_ingest_adapters Read bighub_ingest_batch Read bighub_ingest_event Read bighub_ingest_lifecycle Read bighub_ingest_lifecycles Read bighub_ingest_pending Read bighub_ingest_reconcile Read bighub_ingest_stale Read bighub_ingest_stats Read bighub_insights_advise Read bighub_insights_patterns Read bighub_insights_profile Read bighub_learning_backfill Read bighub_learning_runs Read bighub_learning_strategy Read bighub_outcomes_analytics Read bighub_outcomes_get Read bighub_outcomes_get_by_case Read bighub_outcomes_get_by_validation Read bighub_outcomes_partner_view Read bighub_outcomes_pending Read bighub_outcomes_recommendation_quality Read bighub_outcomes_report Read bighub_outcomes_report_batch Read bighub_outcomes_taxonomy Read bighub_outcomes_timeline Read bighub_precedents_query Read bighub_precedents_signals Read bighub_precedents_stats Read bighub_retrieval_compare Read bighub_retrieval_index_case Read bighub_retrieval_query Read bighub_retrieval_query_explained Read bighub_retrieval_stats Read bighub_retrieval_strategies Read bighub_retrieval_strategy Read bighub_simulations_accuracy Read bighub_simulations_by_request Read bighub_simulations_compare Read bighub_simulations_get Read bighub_simulations_list Read bighub_simulations_stats Read bighub_webhooks_deliveries Read bighub_webhooks_get Read bighub_webhooks_list Read bighub_webhooks_list_events Read bighub_webhooks_replay_failed_delivery Read bighub_webhooks_test Read bighub_webhooks_verify_signature

// FAQ

Can an AI agent delete data through the BIGHUB MCP server? +

Yes. The BIGHUB server exposes 4 destructive tools including bighub_api_keys_delete, bighub_constraints_delete, bighub_constraints_purge_idempotency. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through BIGHUB? +

The BIGHUB server has 17 write tools including bighub_actions_live_connect, bighub_actions_live_disconnect, bighub_api_keys_create. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.

How many tools does the BIGHUB MCP server expose? +

125 tools across 4 categories: Destructive, Execute, Read, Write. 100 are read-only. 25 can modify, create, or delete data.

How do I add Intercept to my BIGHUB setup? +

One line change. Instead of running the BIGHUB server directly, prefix it with Intercept: intercept -c bighub.yaml -- npx -y @@bighub/bighub-mcp. Download a pre-built policy from policylayer.com/policies/bighub and adjust the limits to match your use case.

// RELATED SERVERS

Other MCP servers with similar tools.

Starter policies available for each. Same risk classification, same one-command setup.

policylayer/intercept

Control every MCP tool call
your agent makes.

Set budgets, approvals, and hard limits across MCP servers.

npx -y @policylayer/intercept init

Protect your agent in 30 seconds. Scans your MCP config and generates enforcement policies for every server.

BIGHUB

One command. Full control.

Other MCP servers with similar tools.

Control every MCP tool call your agent makes.

Control every MCP tool call
your agent makes.