Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

BIGHUB

NPM · @BIGHUB/BIGHUB-MCP · SCANNED SEP 25

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

Available components

0 this week 75 Trust /100
Trust breakdown (7 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 → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 31 of 95 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability54
  • AI-judged instruction clarity (fair).Partial
  • 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 Management87
  • Stability observed for 26 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
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 8 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "bighub_constraints_delete" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 125 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the BIGHUB MCP server?

BIGHUB runs locally as an npm package, launched with npx -y @bighub/bighub-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @bighub/bighub-mcp

# add to Claude Code
claude mcp add io-bighub-mcp -- npx -y @bighub/bighub-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "io-bighub-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@bighub/bighub-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "io-bighub-mcp": {
      "command": "npx",
      "args": [
        "-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"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "io-bighub-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@bighub/bighub-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add io-bighub-mcp -t stdio -c npx -a -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.

  • 25 Sept 26 +1
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 23 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 22 Sept 26 +1
    • Stability: 0.97 → pass security
  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 −3
    • Security disclosure: unverified → fail ▼ functional
    • Stability: pass → 0.80 functional
  • 15 Sept 26 +1
    • Stability: 0.97 → pass security
  • 14 Sept 26 0
    • Security disclosure: fail → unverified ▼ functional
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 25 Sept 2026 · Analysed npm/@bighub/bighub-mcp@0.2.1

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 95 packages
Packages resolved 95
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

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. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
bighub_constraints_update ~43

Update a rule by rule_id.

NameTypeReqDescription
idempotency_keystring––
payloadobjectyes–
rule_idstringyes–

Structured output declared, but exposes no named fields.

No examples provided.

bighub_constraints_validate ~23

Validate a rule payload.

NameTypeReqDescription
payloadobjectyes–

No output schema declared.

No examples provided.

bighub_constraints_validate_dry_run ~28

Dry-run validate a rule payload.

NameTypeReqDescription
payloadobjectyes–

No output schema declared.

No examples provided.

bighub_constraints_versions ~33

List historical versions for a rule.

NameTypeReqDescription
limitinteger––
rule_idstringyes–

Structured output declared, but exposes no named fields.

No examples provided.

bighub_events_list ~53

List event stream entries.

NameTypeReqDescription
event_typestring––
limitinteger––
offsetinteger––
rule_idstring––
severitystring––

Structured output declared, but exposes no named fields.

No examples provided.

bighub_events_stats ~16

Get aggregate event stats.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

bighub_features_compare ~75

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

NameTypeReqDescription
case_id_astring––
case_id_bstring––
changed_onlyboolean–Only return features that differ
snapshot_id_astring––
snapshot_id_bstring––

Structured output declared, but exposes no named fields.

No examples provided.

bighub_features_compute ~58

Compute decision features for a case.

NameTypeReqDescription
advisory_dataobject––
case_dataobjectyes–
case_idstringyes–
org_idstringyes–
precedent_dataobject––

Structured output declared, but exposes no named fields.

No examples provided.

bighub_features_compute_batch ~34

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

NameTypeReqDescription
casesarrayyes–

Structured output declared, but exposes no named fields.

No examples provided.

bighub_features_explain ~35

Explain computed features for a case.

NameTypeReqDescription
case_idstringyes–
feature_keystring––

Structured output declared, but exposes no named fields.

No examples provided.

bighub_features_export ~26

Export all features for a case.

NameTypeReqDescription
case_idstringyes–

Structured output declared, but exposes no named fields.

No examples provided.

bighub_features_export_batch ~33

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

NameTypeReqDescription
case_idsarrayyes–

Structured output declared, but exposes no named fields.

No examples provided.

bighub_features_get_snapshot ~27

Get a feature snapshot by ID.

NameTypeReqDescription
snapshot_idstringyes–

Structured output declared, but exposes no named fields.

No examples provided.

bighub_features_list_snapshots ~32

List feature snapshots.

NameTypeReqDescription
case_idstring––
tagstring––

Structured output declared, but exposes no named fields.

No examples provided.

bighub_features_schema ~22

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

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

bighub_features_snapshot ~36

Create a versioned feature snapshot for a case.

NameTypeReqDescription
case_idstringyes–
tagstring––

Structured output declared, but exposes no named fields.

No examples provided.

bighub_features_stats ~16

Get feature layer statistics.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

bighub_http_request ~67

Low-level passthrough for any BIGHUB API endpoint.

NameTypeReqDescription
body–––
headersobject––
idempotency_keystring––
methodstringyes–
pathstringyes–
queryobject––

Structured output declared, but exposes no named fields.

No examples provided.

bighub_ingest_adapters ~22

List available ingestion adapters and domain normalizers.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

bighub_ingest_batch ~67

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

NameTypeReqDescription
adapterstring––
domainstring––
eventsarrayyesRaw event payloads

Structured output declared, but exposes no named fields.

No examples provided.

bighub_ingest_event ~398

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.

NameTypeReqDescription
actionobject–Action payload: {tool, action, arguments, value, target, domain}
adapterstring––
case_idstring–Link to DecisionCase
contextobject–Context: {risk_score, axes, environment, ...}
domainstring––
entity_idstring–Entity being acted on
event_typestring–Event type: ACTION_PROPOSED, ACTION_EXECUTED, ACTION_BLOCKED, HUMAN_OVERRIDE, HUMAN_APPROVAL, HUMAN_REJECTION, OUTCOME_OBSERVED, OUTCOME_UPDATED, ROLLBACK_PERFORMED, CORRECTION_APPLIED, ESCALATION_TR…
executionobject–Execution result: {executed, status_code, error, ...}
external_refstring–Your system's reference (e.g. order_id)
human_feedbackobject–Human: {feedback_type, decision, reason, ...}
intentobject–Intent: {goal_summary, trigger_source, actor_type, ...}
outcomeobject–Outcome: {status, description, revenue_impact, ...}
request_idstring–Link to BIGHUB decision (from /actions/evaluate response)
session_idstring–Session / conversation ID
tagsarray––
tenant_refstring–Tenant-level reference
timestampstring–ISO 8601 timestamp (defaults to now)
validation_idstring–Link to rule validation

Structured output declared, but exposes no named fields.

No examples provided.

bighub_ingest_lifecycle ~62

Get a specific decision lifecycle by correlation key.

NameTypeReqDescription
case_idstring––
entity_idstring––
external_refstring––
request_idstring––
tenant_refstring––

Structured output declared, but exposes no named fields.

No examples provided.

bighub_ingest_lifecycles ~44

List decision lifecycles with optional status filter.

NameTypeReqDescription
limitinteger––
status_filterstring–Filter by lifecycle status

Structured output declared, but exposes no named fields.

No examples provided.

bighub_ingest_pending ~27

List lifecycles awaiting outcome reconciliation.

NameTypeReqDescription
limitinteger––

Structured output declared, but exposes no named fields.

No examples provided.

bighub_ingest_reconcile ~91

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

NameTypeReqDescription
key_namestringyesCorrelation key: request_id, case_id, external_ref, tenant_ref, or entity_id
key_valuestringyesValue of the correlation key
outcomeobjectyesOutcome event payload to attach

Structured output declared, but exposes no named fields.

No examples provided.

bighub_ingest_stale ~45

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

NameTypeReqDescription
limitinteger––
stale_after_daysinteger––

Structured output declared, but exposes no named fields.

No examples provided.

bighub_ingest_stats ~28

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

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

bighub_insights_advise ~62

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

NameTypeReqDescription
actionstringyes–
actor_typestring––
domainstringyes–
risk_bandstring––
toolstringyes–

Structured output declared, but exposes no named fields.

No examples provided.

bighub_insights_learn ~20

Trigger pattern learning from accumulated cases.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

bighub_insights_patterns ~48

List detected decision patterns.

NameTypeReqDescription
domainstring––
min_severitystring––
pattern_typestring––
toolstring––

Structured output declared, but exposes no named fields.

No examples provided.

bighub_insights_profile ~43

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

NameTypeReqDescription
actionstring––
domainstring––
toolstring––

Structured output declared, but exposes no named fields.

No examples provided.

bighub_kill_switch_activate ~76

Activate global/domain kill switch. Requires a reason.

NameTypeReqDescription
domainstring–Domain to target (when scope=domain)
reasonstringyesWhy the kill switch is being activated
rule_idstring–Specific rule to kill
scopestring–Scope: global or domain

No output schema declared.

No examples provided.

bighub_kill_switch_deactivate ~71

Deactivate kill switch by switch_id. Requires a reason.

NameTypeReqDescription
domainstring––
reasonstringyesWhy the kill switch is being deactivated
rule_idstring––
scopestring––
switch_idstringyes–

No output schema declared.

No examples provided.

bighub_kill_switch_status ~18

Read kill switch status.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

bighub_learning_backfill ~57

Backfill learning artifacts from historical outcomes.

NameTypeReqDescription
action_familystring––
async_modeboolean––
domainstring––
forceboolean––
limitinteger––

Structured output declared, but exposes no named fields.

No examples provided.

bighub_learning_recompute ~59

Trigger recomputation of learning artifacts for a scope.

NameTypeReqDescription
action_familystring––
async_modeboolean––
domainstring––
forceboolean––
limitinteger––

Structured output declared, but exposes no named fields.

No examples provided.

bighub_learning_runs ~24

List recent learning pipeline runs.

NameTypeReqDescription
limitinteger––

Structured output declared, but exposes no named fields.

No examples provided.

bighub_learning_strategy ~19

Get current learning strategy version and configuration.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

bighub_outcomes_analytics ~38

Outcome analytics summary.

NameTypeReqDescription
domainstring––
sincestring––
untilstring––

Structured output declared, but exposes no named fields.

No examples provided.

bighub_outcomes_get ~26

Get outcome by request_id.

NameTypeReqDescription
request_idstringyes–

Structured output declared, but exposes no named fields.

No examples provided.

bighub_outcomes_get_by_case ~28

Get outcome by case_id.

NameTypeReqDescription
case_idstringyes–

Structured output declared, but exposes no named fields.

No examples provided.

bighub_outcomes_get_by_validation ~28

Get outcome by validation_id.

NameTypeReqDescription
validation_idstringyes–

Structured output declared, but exposes no named fields.

No examples provided.

bighub_outcomes_partner_view ~60

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

NameTypeReqDescription
domainstringyesThe domain to generate the partner view for

No output schema declared.

No examples provided.

bighub_outcomes_pending ~35

List decisions still awaiting outcome reports.

NameTypeReqDescription
limitinteger––
min_age_hoursinteger––

Structured output declared, but exposes no named fields.

No examples provided.

bighub_outcomes_recommendation_quality ~98

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.

NameTypeReqDescription
domainstring–Filter by domain
sincestring–Start date (ISO 8601)
untilstring–End date (ISO 8601)

No output schema declared.

No examples provided.

bighub_outcomes_report ~182

Report a real-world outcome linked to a decision.

NameTypeReqDescription
actual_impactobject––
case_idstring––
correction_costnumber––
correction_descriptionstring––
correction_neededboolean––
customer_impact_countinteger––
descriptionstring––
detailsobject––
observed_atstring––
reported_bystring––
request_idstring––
revenue_impactnumber––
rollback_performedboolean––
statusstringyes–
support_tickets_createdinteger––
tagsarray––
time_to_detect_snumber––
time_to_resolve_snumber––
validation_idstring––

Structured output declared, but exposes no named fields.

No examples provided.

bighub_outcomes_report_batch ~28

Batch report outcomes (max 100).

NameTypeReqDescription
outcomesarrayyes–

Structured output declared, but exposes no named fields.

No examples provided.

bighub_outcomes_taxonomy ~18

Supported outcome status taxonomy.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

bighub_outcomes_timeline ~29

Get full outcome timeline for a request.

NameTypeReqDescription
request_idstringyes–

Structured output declared, but exposes no named fields.

No examples provided.

bighub_precedents_query ~95

Query similar past decision cases.

NameTypeReqDescription
actionstringyes–
actor_typestring––
axesobject––
domainstringyes–
intentstring––
max_resultsinteger––
min_similaritynumber––
require_outcomeboolean––
risk_scorenumber––
toolstring––

Structured output declared, but exposes no named fields.

No examples provided.

Common questions

What is the BIGHUB MCP server?

BIGHUB is an MCP server listed in the public MCP registry as io.bighub/mcp. Decision learning for AI agent actions. Evaluate, score, decide, and learn from outcomes. This page covers its npm package (@bighub/bighub-mcp).

Is the BIGHUB MCP server safe to use?

BIGHUB scores 75 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 25 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the BIGHUB MCP server expose?

BIGHUB exposes 125 tools: bighub_http_request, bighub_actions_evaluate, bighub_actions_evaluate_payload, bighub_actions_dry_run, bighub_actions_live_connect, and 120 more. Their descriptions and schemas cost roughly 5,931 tokens of context every time the server is loaded.

Is the BIGHUB MCP server still maintained?

BIGHUB is still listed as active in the MCP registry. We last reached this channel on 25 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the BIGHUB MCP server under?

BIGHUB declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.