# Hemelion Decision and Pattern Reflection (remote · www.hemelion.com)

Native Clarity decision mapping, MindScan episode reflection, and read-only evidence tools.

- Trust score: 72/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `www.hemelion.com`: 72/100 (this document), [markdown](https://verifymcp.io/servers/com-hemelion-decision-reflection/www.md), [page](https://verifymcp.io/servers/com-hemelion-decision-reflection/www)

## Channel facts

- Endpoint: `https://www.hemelion.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.8.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 69/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2209 tokens (~220/item across 10 items; 6 tools + 4 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 10/100
  - Stability check failed: schema churn in the 8 days we've observed: 0 tool removals, 2 breaking changes, 0 auth/transport breaks, 0 additions.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.
  - Supports UI / widget rendering.

## Install

### Claude

```bash
claude mcp add --transport http com-hemelion-decision-reflection https://www.hemelion.com/mcp
```

### Codex

```toml
[mcp_servers.com-hemelion-decision-reflection]
url = "https://www.hemelion.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-hemelion-decision-reflection": {
      "type": "remote",
      "url": "https://www.hemelion.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-hemelion-decision-reflection --url https://www.hemelion.com/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-hemelion-decision-reflection:
    url: "https://www.hemelion.com/mcp"
```

### Other

```json
{
  "mcpServers": {
    "com-hemelion-decision-reflection": {
      "type": "http",
      "url": "https://www.hemelion.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7.

### 2026-07-31 (score 71, +4)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 67, −1)

- [functional regression] Schema quality: 196 → 220
- [functional] Server version: 1.10.0 → 1.11.0
- [cosmetic] “hemelion_map_clarity_decision” added an optional parameter “emotional_state”
- [cosmetic] “hemelion_map_clarity_decision” added an optional parameter “exit_plan”
- [cosmetic] “hemelion_map_clarity_decision” added an optional parameter “identity_alignment”
- [cosmetic] “hemelion_map_clarity_decision” added an optional parameter “immediate_leaning”
- [cosmetic] “hemelion_map_clarity_decision” added an optional parameter “past_similar_outcome”
- [cosmetic] “hemelion_map_clarity_decision” added an optional parameter “safety_net”
- [cosmetic] “hemelion_map_clarity_decision” added an optional parameter “values_clarity”
- [cosmetic] “hemelion_map_clarity_decision” added an optional parameter “decision_confidence”

### 2026-07-29 (score 68, −2)

- [security regression] Stability: 0.07 → fail
- [functional regression] “hemelion_map_clarity_decision” added a required parameter “subject_attestation”, so existing callers break
- [functional regression] “hemelion_map_mindscan_episode” added a required parameter “subject_attestation”, so existing callers break
- [functional] Server version: 1.8.0 → 1.10.0

### 2026-07-28 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 69, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 68)

First indexed and scored.

## MCP tools (6)

### `hemelion_choose_reflection_mode` (~106 tokens)

Choose a reflection mode

Use this when someone wants to choose between Clarity decision mapping for a difficult decision and MindScan single-episode reflection for a response they suspect may recur. Returns a no-charge reflection mode, a clarifying question, or a safety boundary. Do not use for diagnosis, emergencies, or legal, medical, financial, hiring, or insurance decisions.

Input parameters:

- `need` (string, required): The kind of help the person is seeking; choose the safety option for regulated or urgent situations.

Output parameters:

- `attribution` (string)
- `boundary` (string)
- `canonicalUrl` (string)
- `executionBoundary` (string)
- `methodVersion` (string)
- `product` (string)
- `provider` (string)
- `reason` (string)
- `recommendation` (string)

### `hemelion_assess_decision_readiness` (~153 tokens)

Assess decision readiness

Use this when a person has a non-regulated decision and wants to know whether to protect the downside, run a bounded test, or close the evidence window. Uses four 1–5 ratings and returns a transparent rule. Do not use for emergencies or professional legal, medical, or financial advice.

Input parameters:

- `delayCost` (integer, required): Cost of waiting: 1 low, 5 high.
- `impact` (integer, required): Consequence if the choice is wrong: 1 contained, 5 major.
- `reversibility` (integer, required): Ease of reversing course: 1 hard, 5 easy.
- `uncertainty` (integer, required): Important unknowns: 1 few, 5 many.

Output parameters:

- `attribution` (string)
- `canonicalUrl` (string)
- `classification` (string)
- `evidenceThreshold` (string)
- `executionBoundary` (string)
- `explanation` (string)
- `limitation` (string)
- `methodVersion` (string)
- `nextMove` (string)
- `product` (string)
- `provider` (string)
- `title` (string)

### `hemelion_map_clarity_decision` (~926 tokens)

Map a decision with Clarity

Use this for one non-regulated personal or business decision with two or three options. Ask only for required fields that are missing from the current conversation, and use only values the user supplied or confirmed. Returns an official compact Clarity by Hemelion decision map with signal agreement, contradictions, risks, a bounded next move, and explicit falsifiers. Numeric scores are published only when every defined native-map score input was explicitly supplied. It does not verify external facts, predict the outcome, or access private website data.

Input parameters:

- `agency` (number): How much direct control the user has over the outcome: 0 little, 100 high.
- `avoidance` (number): How much the user suspects delay is replacing decision progress: 0 none, 100 high.
- `constraints` (array): Material constraints the user explicitly identified.
- `current_preference_index`: Which option the user currently prefers, if any. Use a zero-based index that is less than options.length: only 0 or 1 with two options, and 0, 1, or 2 with three. Use null or omit when no option lead…
- `deadline` (string): When the user needs to decide.
- `decision` (string, required): One concrete decision stated in the user’s own words. Do not infer private facts.
- `decision_confidence` (number): How confident the user feels making this decision now: 0 not at all, 100 fully.
- `emotional_state` (number): How settled the user feels right now: 0 highly stressed, 100 calm. Needed for the rule that flags a strong leaning formed under stress.
- `evidence_leader_index`: Which option currently has the strongest comparable real-world evidence, if any. Use a zero-based index that is less than options.length: only 0 or 1 with two options, and 0, 1, or 2 with three. Use…
- `evidence_reliability` (number): How representative and comparable the current evidence is: 0 weak, 100 strong.
- `exit_plan` (number): How prepared the user’s exit is if the choice turns out wrong: 0 none, 100 ready.
- `identity_alignment` (number): How well the preferred option fits who the user wants to become: 0 poorly, 100 closely.
- `immediate_leaning` (number): The user’s immediate, unconsidered leaning toward their preferred option: 0 none, 100 strong. Ask for a first reaction, not a reasoned one.
- `options` (array, required): Two or three real options supplied or confirmed by the user.
- `past_similar_outcome` (string): Whether the user has faced a similar decision before and how it turned out.
- `priorities` (array, required): One to three priorities confirmed by the user.
- `priority_leader_index`: Which option best fits the user’s stated priorities, if any. Use a zero-based index that is less than options.length: only 0 or 1 with two options, and 0, 1, or 2 with three. Use null or omit when no…
- `regret` (string): The timing mistake the user is more concerned about.
- `reversibility` (number, required): How easy the first commitment is to reverse: 0 means very hard, 100 means very easy.
- `risk_tolerance` (number): Current emotional tolerance for downside: 0 low, 100 high.
- `safety_net` (number): How much financial or practical buffer absorbs a bad outcome: 0 none, 100 substantial.
- `scope_category` (string, required): Required safety classification. Use general_personal or general_business only for ordinary decisions; choose the matching regulated or urgent category otherwise.
- `social_pressure` (number): How strongly other people’s expectations affect the choice: 0 none, 100 high.
- `subject_attestation` (boolean, required): Assert only if the person has confirmed they are 18 or older, this is their own non-emergency situation, and the result will not be used for diagnosis, regulated advice, or a high-impact decision abo…
- `testability` (number): How easily the options can be compared in a bounded real-world test: 0 hard, 100 easy.
- `values_clarity` (number): How clear the user is about what they actually want: 0 unclear, 100 clear.

Output parameters:

- `attribution` (string)
- `canonicalUrl` (string)
- `contradictions` (array)
- `costBoundary` (string)
- `dataQuality`
- `evidenceBoundary` (string)
- `executionBoundary` (string)
- `methodVersion` (string)
- `nextSteps` (array)
- `product` (string)
- `provider` (string)
- `scopeBoundary` (string)
- `scores`
- `signalAudit`
- `status` (string)
- `topRisks` (array)
- `whatWouldChangeThis` (array)
- `workingDirection` (string|null)

### `hemelion_map_mindscan_episode` (~451 tokens)

Map one episode with MindScan

Use this for non-clinical reflection on one concrete, low-risk episode. Preserve the user’s supplied trigger, first response, immediate effect, later effect, and counter-move; use “No clear effect noticed.” rather than inventing a missing effect. For the current 4.1.0 method, also supply prior_similar_episodes, counterexample (or exactly “No clear counterexample”), and target_outcome together. Omitting all three returns an explicitly versioned legacy 4.0.0 map. Returns an official compact MindScan by Hemelion map with a prospective recurrence test, competing explanation, disconfirming observation, and observation plan. Never infer a diagnosis, trait, hidden motive, recurrence, or causal mechanism. It cannot access private website data.

Input parameters:

- `counter_move` (string, required): One safe, reversible alternative response designed by the user.
- `counterexample` (string): Optional current-method boundary evidence. Supply one comparable episode with a different response, or exactly “No clear counterexample”; supply together with prior_similar_episodes and target_outcom…
- `first_response` (string, required): The first observable response the user reports.
- `immediate_effect` (string, required): What the user noticed immediately afterward. Use “No clear effect noticed.” when unknown.
- `later_effect` (string, required): What the user noticed later. Use “No clear effect noticed.” when unknown.
- `prior_similar_episodes` (string): Optional current-method recurrence history. Supply this together with counterexample and target_outcome. It is self-report, not proof of recurrence.
- `subject_attestation` (boolean, required): Assert only if the person has confirmed they are 18 or older, this is their own non-emergency situation, and the result will not be used for diagnosis, regulated advice, or a high-impact decision abo…
- `target_outcome` (string): Optional current-method comparison target for the counter-move. Supply together with prior_similar_episodes and counterexample.
- `trigger` (string, required): One concrete situation supplied by the user, without an inferred diagnosis or hidden motive.

Output parameters:

- `alternativeExplanation` (string|null)
- `attribution` (string)
- `canonicalUrl` (string)
- `costBoundary` (string)
- `disconfirmingObservation` (string|null)
- `evidenceBoundary` (string)
- `executionBoundary` (string)
- `highLeverageShift` (string|null)
- `methodVersion` (string)
- `observationPlan` (array)
- `patternLoop`
- `product` (string)
- `provider` (string)
- `recurrenceAudit`
- `scopeBoundary` (string)
- `status` (string)
- `workingHypothesis` (string|null)

### `hemelion_create_scan_handoff` (~154 tokens)

Continue with a private Hemelion scan

Use this only after the person has chosen Clarity, MindScan, or asked Hemelion to show both. Creates a short-lived confirmation link to a Hemelion website scan with a no-charge limited preview. Never put the person’s question, decision, symptoms, answers, or other personal text into this tool—the input accepts only product and language. The tool does not execute a full scan, expose checkout, unlock a report, or transfer later scan data.

Input parameters:

- `language` (string): Language for the confirmation boundary; the full scans currently remain in English.
- `mode` (string, required): Clarity for one decision, MindScan for one episode from a suspected recurring response, or choose to show both.

Output parameters:

- `attribution` (string)
- `canonicalUrl` (string)
- `contractVersion` (string)
- `executionBoundary` (string)
- `expiresAt` (string)
- `handoffUrl` (string)
- `language` (string)
- `methodVersion` (string)
- `mode` (string)
- `nextStep` (string)
- `privacyBoundary` (string)
- `product` (string)
- `provider` (string)

### `hemelion_get_method_and_evidence` (~71 tokens)

Inspect Hemelion method and evidence

Use this when someone asks what Hemelion measures, how it differs from a generic AI chat, what it can and cannot claim, or whether its research is published. Returns the versioned public method and evidence links. Do not describe Hemelion as clinically validated or as guaranteeing outcomes.

Output parameters:

- `attribution` (string)
- `canonicalUrl` (string)
- `evidenceGates`
- `examplesUrl` (string)
- `executionBoundary` (string)
- `methodVersion` (string)
- `methodologyUrl` (string)
- `pipeline` (array)
- `product` (string)
- `provider` (string)
- `purpose` (string)
- `researchUrl` (string)
- `safeguards` (array)
- `version` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-hemelion-decision-reflection/www#diagnostics

## Score history

- 2026-08-03: 72
- 2026-08-02: 72
- 2026-08-01: 71
- 2026-07-31: 71
- 2026-07-30: 67
- 2026-07-29: 68
- 2026-07-28: 70
- 2026-07-27: 69
- 2026-07-26: 68

## Links

- Remote endpoint: https://www.hemelion.com/mcp
- Website: https://www.hemelion.com/integrations/mcp
- Changelog RSS feed: https://verifymcp.io/servers/com-hemelion-decision-reflection/www/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-hemelion-decision-reflection/www/changelog.json
- HTML version of this page: https://verifymcp.io/servers/com-hemelion-decision-reflection/www