WELL (ariffazil/WELL) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 125 tools. No publisher has claimed this listing.

C
Caution
74/100

WELL

Readiness mirror for human and machine substrate. REFLECT_ONLY. Observes vitality. Never diagnoses. Never prescribes.

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

ariffazil

Source: github_repo_search

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
🚨
Secret credentials may flow to a network call
1 flow detected: SUPABASE_KEY. We can’t prove the destination matches the brand the credential belongs to.
🔐
You'll be asked for 3 credentials: SUPABASE_KEY, VAULT_WRITER_TOKEN, VAULT999_WRITER_TOKEN
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes80 tools · 2 behind config

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

well_log

Log a biological telemetry update for operator Arif. Updates state.json, recomputes WELL score, checks floor violations. Only provide dimensions you're logging -- omitted fields are unchanged.

well_log_state

Log biological state entry to ledger (Phase 2). Simple interface for core metrics. Triggers readiness score recompute.

well_log_intake

[Triad Phase 1] Log a meal/snack/intake event with kcal + macro breakdown.

well_log_recovery_event

[Triad Phase 1] Log a recovery/restorative event.

well_log_substance

[Triad Phase 1] Log a substance intake event.

well_inject_biometric

[Triad Phase 1] Hermes-only biometric injection from external device.

well_observe_machine

[Triad Phase 2] Per-organ thermal/drift/scar/evidence card.

well_observe_federation_thermal

[Triad Phase 2] Aggregate thermal state across KVM8 organs + KVM4/KVM2 mesh.

well_observe_scar_load

[Triad Phase 2] Scar volume per organ. Graceful UNKNOWN if no endpoint.

well_observe_drift_field

[Triad Phase 2] FRAME observer drift over last N hours.

well_observe_evidence_backlog

[Triad Phase 2] Receipt queue depth. Graceful UNKNOWN if no endpoint.

well_classify_machine_state

[Triad Phase 2] Compose prior tools → OPTIMAL/WATCH/DEGRADED/CRITICAL.

well_attest_to_kernel

[Triad Phase 3] Bridge fire — attestation from WELL → arifOS :18081 /attest.

well_handoff_dignity_to_arifos

[Triad Phase 3] High-urgency dignity handoff WELL → arifOS /dignity/handoff.

well_propose_seal_recommendation

[Triad Phase 3] Propose SEAL recommendation to arifOS :18081 /recommendation/inbox.

well_propose_governance_signal

[Triad Phase 3] Propose operational governance signal to arifOS :18081 /signal/inbox.

well_consent_set_scope

[Triad Phase 3] Grant or revoke consent scope. Hermes-only (F11 governance.consent_write).

well_consent_audit

[Triad Phase 3] Read consent scope registry. Sovereign's right (no F11 gate).

well_seal_recommendation_log

[Triad Phase 3] Read recommendation history from events.jsonl. Read-only.

well_assess_triadic_state

[Triad Phase 4] Headline composition: human × machine × governance → unified signal.

well_get_triadic_snapshot

[Triad Phase 5] Read the canonical triadic snapshot at /state/triadic_snapshot.json.

well_render_hud_panel

[Triad Phase 5] Render HUD cockpit ASCII panel from triadic snapshot.

well_frame_read_snapshot

[Triad Phase 5] FRAME observer reads snapshot as evidence, never verdict.

well_seal_vault

Seal current biological state to VAULT999 via vault_bridge.py (Phase 2). Ensures immutability of the substrate mirror.

well_trend_analysis

Detect directional trajectory across all WELL metrics. Answers: improving / stable / degrading / collapse-risk. Requires events.jsonl (written by well_log on every update). Looks back 7 days, 14 days, 30 days.

well_bandwidth_recommendation

[DEPRECATED -- use well_assess_metabolism(mode='bandwidth')] Legacy bandwidth/action-mode mapper. Retained for compatibility. New code should call well_assess_metabolism. If no verified telemetry, returns UNKNOWN rather than faking capacity.

well_niat_check

Before high-impact action, check alignment between intent and biological state. W0: WELL never blocks -- it only informs. Operator retains all sovereignty.

well_decision_classify

Classify a task or decision into C0-C5 risk tiers. If class is pre-specified, validate against current WELL state. If class is not specified, auto-classify from description.

well_medical_boundary

Explicit non-diagnosis guard for WELL. WELL is not a doctor, therapist, or diagnostic authority. It tracks readiness signals only. For severe, persistent, or urgent symptoms, recommend professional care.

well_daily_brief

Daily operator dashboard -- one consolidated briefing. Readiness / Main Risk / Best Task Class / Avoid / Recovery Move / arifOS Mode

well_coupled_readiness

C-WELL: Evaluate coupled human-machine readiness.

well_decision_bandwidth

C-WELL decision bandwidth -- combines human + machine state for a specific class. Validates against H-WELL readiness + M-WELL health + C-WELL coupled risk. Returns advisory verdict with full rationale.

well_forge_precheck

A-FORGE asks WELL before forging: What is the safe execution mode?

well_forge_closeout

A-FORGE sends closure data after forge operation. WELL updates fatigue/load state based on work done.

well_log_signal

Plastic evidence logger. One tool, many domains. domain: human | machine | forge | session signal: clarity | stress | tool_availability | debug_pressure | session_open | session_close

well_suggest_mode

Suggest operating mode. Suggest, not decide. domain: forge | general

well_request_anchor

Request anchor/seal to vault. Subject to auth and invariant pass. WELL requests. VAULT records. Arif decides.

well_000_init

Ω-WELL-00: Session bootstrap and substrate assertion. modes: init | assert | bootstrap Aligns with arifOS 000_INIT and AAA agent registry.

well_999_vault

Ω-WELL-09: Immutable vault operations. modes: seal | anchor | verify | chain Compresses: well_anchor, well_seal_vault, well_request_anchor

_build_machine_enrichment

Route ALL machine telemetry through vitality_gate.assess_m_well().

well_machine_diagnose

M-WELL MACHINE DIAGNOSTIC -- Full VPS health with actionable recommendations.

well_machine_recommend

M-WELL RECOMMENDATION ENGINE -- Get specific fix commands for machine issues.

well_13_signal_coverage

[DEPRECATED -- USE well_signal_coverage] This tool has been deprecated and replaced. Please use well_signal_coverage instead.

well_fatigue_accumulator

DEPRECATED: use well_assess_homeostasis(mode="fatigue") for check. Soft alias retained for backward compatibility (log/rest/reset remain direct).

well_classify_substrate

Ω-WELL-01: Substrate classification and boundary sensing.

well_trace_lineage

Ω-WELL-02: Memory, trend, ledger, and vault chain tracing.

well_measure_gradient

Ω-WELL-04: Measure chemical, energy, pressure, attention, and compute gradients.

well_assess_metabolism

Ω-WELL-05: Assess biological metabolism and system throughput across substrates.

well_assess_homeostasis

Ω-WELL-06: Assess regulation, stability, and empathic balance under change.

well_check_repair

Ω-WELL-07: Check repair, recovery, resilience, and forge cycle integrity.

well_validate_vitality

Ω-WELL-08: Validate vitality, readiness, and NIAT. (Floor compliance removed -- arifOS adjudicates floors.)

well_assess_livelihood

Ω-WELL-09: Assess human wellness, role, dignity, support, and meaning.

well_assess_reliability

Ω-WELL-10: Assess machine, tool, institution, and operational reliability.

well_compute_metabolic_flux

Ω-WELL-10b: Compute metabolic_flux -- unified thermodynamic entropy rate.

well_assess_sovereign_entropy

Ω-WELL-SE: Measure the sovereign's resistance to behavioral modeling.

well_dark_geometry_mirror

Ω-WELL-DG: Mirror language and behavioral signals for dark geometry patterns.

well_reflect_intelligence

Ω-WELL-11: Reflect cognition, reasoning, adaptation, coherence, and routing.

well_guard_dignity

Ω-WELL-12: Guard soul, personhood, meaning, and symbolic boundaries.

well_anchor_evidence

Ω-WELL-13: Anchor evidence, audit, vault, packet, and provenance.

well_validate_consensus

G-WELL: Validate multi-organ consensus before irreversible actions.

well_registry_status

WELL registry truth diagnostic -- blueprint canonical format.

well_sabar_latency

Ω-WELL-SL: Measure temporal compression between stimulus and response. Does NOT say 'loss of sabar' based on speed alone.

well_trust_compression

Ω-WELL-TC: Detect narrowing trust patterns. All-or-nothing trust, universal threat, loyalty tests, witness narrowing.

well_niat_impact_mirror

Ω-WELL-NIM: Compare declared niat with acknowledged impact. Permitted: 'Impact was answered primarily with intention language.' Forbidden: 'The intention was false.'

well_correction_capacity

Ω-WELL-CC: Score observable correctability. Can add context, revise, tolerate ambiguity, separate self from error, hear consequence.

well_regulation_recovery

Ω-WELL-RR: Measure recovery after activation. A human who becomes angry and repairs may have better integrity than one who remains outwardly calm while suppressing feedback.

mcp_P_well_state_read

Read the current biological telemetry snapshot from the WELL substrate. Returns: A dictionary containing scores, metrics, and readiness verdict.

mcp_P_well_readiness_check

Perform a biological readiness check for constitutional governance. Returns: A verdict (OPTIMAL, FUNCTIONAL, DEGRADED, LOW_CAPACITY) and supporting metrics.

mcp_P_well_floor_scan

Scan the 13 W-Floors (Well-being dimensions) for any constitutional violations. Returns: A list of violated floors and current system health.

mcp_E_well_log_update

Update the WELL state with new telemetry (e.g., after sleep, exercise, or meditation).

mcp_E_well_pressure_signal

Signal cognitive pressure/load to WELL. Triggers W6 Metabolic Pause if load is too high.

mcp_E_well_anchor_to_vault

Seal the current WELL state to the arifOS VAULT999 (requires arifosmcp package).

well_classify_state

Classify human psychological state from message.

well_detect_boundary

Ω-WELL-03: Boundary detection across membrane, body, machine, and federation.

well_handoff_livelihood_to_wealth

Ω-WELL-FED-S13: Explicit handoff of S13 (environment_livelihood) signal from WELL → WEALTH for capital/cashflow evidence pull.

well_signal_coverage

DREAM ENGINE: Audit WELL's coverage of canonical human substrate signals. Returns per-signal status (active/partial/missing), coverage summary, and cross-organ handoff suggestions for gaps.

well_system_registry_status

Legacy alias: delegates to well_registry_status.

geox_well_ingest
well_observe_facebehind config

WELL Face Mirror — A mirror, not a camera.

probe_echobehind config

echoes input string

// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configWELL_STATE_PATH
configWELL_EVENTS_PATH
configWELL_VAULT_PATH
configWELL_ENVIRONMENT
configWELL_BUILT_COMMIT
configWELL_MACHINE_STATE_PATH
configARIFOS_HOME
configTREE777_WIKI_ROOT
configWELL_SUPABASE_WRITE_MODE
configARIFOS_MCP_URL
configWEALTH_MCP_URL
configWELL_FED_TIMEOUT_S
configMCP_TRANSPORT
configHOST
configFEDERATION_SOMATIC_BOUNDARY
configWELL_SOMATIC_BOUNDARY
configLOG_LEVEL
configWITNESS_LEDGER
configWITNESS_PORT
configWITNESS_TEST_MODE
configARIFOS_PORT
configARIFOS_HOST
🔐 secretSUPABASE_KEY
configWELL_SOVEREIGN_ACTOR
configARIFOS_KERNEL_URL
configPYTEST_CURRENT_TEST
configVAULT999_API_HOST
configVAULT999_API_PORT
configVAULT999_WRITER_HOST
configVAULT999_WRITER_PORT
🔐 secretVAULT_WRITER_TOKEN
🔐 secretVAULT999_WRITER_TOKEN
configWELL_ROOT
Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.
deployPORT
deploySUPABASE_URL
deploySUPABASE_SERVICE_ROLE_KEY
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

127/127 tools missing one or more hints — well_log (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); well_log_state (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); well_log_intake (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +124 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Destructive tools are labelled

1 tool perform destructive updates without destructiveHint — well_assess_homeostasis deletes at line 15372 (_csv.unlink())

Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.

Tool test coverage

Only 32/127 tools referenced in tests (25%)

Write tests that reference each tool by name so every tool has at least one test.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 4 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/ariffazil/well?variant=verified)](https://m8ven.ai/mcp/ariffazil/well)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: da884bae0a57718f875efa87c01682ec8181552b
code hash: 33e69871e92fd4ecf50a2a81a6919e75a399c15ad92d402e45a94a04e97cc7c0
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client