# Moretes Architect MCP (remote · mcp.moretes.com)

Evidence-first architecture workbench: 48 deterministic tools, 10 architect personas, any cloud

- Trust score: 71/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `mcp.moretes.com`: 71/100 (this document), [markdown](https://verifymcp.io/servers/fernando-moretes-moretes-aws-architect-mcp/mcp.md), [page](https://verifymcp.io/servers/fernando-moretes-moretes-aws-architect-mcp/mcp)
- npm · `moretes-aws-architect-mcp`: 81/100, [markdown](https://verifymcp.io/servers/fernando-moretes-moretes-aws-architect-mcp/moretes-aws-architect-mcp.md), [page](https://verifymcp.io/servers/fernando-moretes-moretes-aws-architect-mcp/moretes-aws-architect-mcp)

## Channel facts

- Endpoint: `https://mcp.moretes.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.4.1`

## 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 2026-11-05.

- **Endpoint Security**: 74/100
  - 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.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - 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**: 72/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 3688 tokens (~55/item across 66 items; 48 tools + 18 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (88% of tools); any adoption earns full credit.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "agent_eval_plan" implies "eval" and declares readOnlyHint instead, contradicting what its own name says it does.
  - An AI judge read all 50 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Moretes Architect MCP server?

Moretes Architect MCP is a hosted endpoint at https://mcp.moretes.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http fernando-moretes-moretes-aws-architect-mcp 'https://mcp.moretes.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "fernando-moretes-moretes-aws-architect-mcp": {
      "url": "https://mcp.moretes.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "fernando-moretes-moretes-aws-architect-mcp": {
      "type": "http",
      "url": "https://mcp.moretes.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.fernando-moretes-moretes-aws-architect-mcp]
url = "https://mcp.moretes.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "fernando-moretes-moretes-aws-architect-mcp": {
      "type": "remote",
      "url": "https://mcp.moretes.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add fernando-moretes-moretes-aws-architect-mcp --url 'https://mcp.moretes.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  fernando-moretes-moretes-aws-architect-mcp:
    url: "https://mcp.moretes.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "fernando-moretes-moretes-aws-architect-mcp": {
      "Transport": "http",
      "Url": "https://mcp.moretes.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add fernando-moretes-moretes-aws-architect-mcp -t streamable-http -u 'https://mcp.moretes.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "fernando-moretes-moretes-aws-architect-mcp": {
      "type": "http",
      "url": "https://mcp.moretes.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.

### 2026-11-04 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 68, +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.

### 2026-10-28 (score 67, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-27 (score 67)

First indexed and scored.

## MCP tools (48)

### `architect_panel` (~91 tokens)

Convene architect personas (solution, enterprise, business, data, infrastructure, software, AI, security, governance, FinOps) on a subject: each returns its questions, checks, deliverables and the workbench tools to call. Lens, not a verdict.

Input parameters:

- `artifactType` (string, required)
- `knownFacts` (array, required)
- `roles` (array, required)
- `subject` (string, required)

Output parameters:

- `artifactType` (string|null)
- `availableRoles` (array)
- `howToUse` (string|null)
- `kind` (string|null)
- `knownFacts` (array)
- `limitation` (string|null)
- `panel` (array)
- `sources` (array)
- `subject` (string|null)
- `synthesis` (array)
- `validated` (boolean|null)

### `code_review_architecture` (~81 tokens)

Heuristic architecture and security scan of source code pasted as text (any language): secrets, insecure calls, SQL built by concatenation, disabled TLS, hardcoded endpoints, missing timeouts and retry hazards. Not a linter or SAST replacement.

Input parameters:

- `code` (string, required)
- `filename` (string, required)
- `language` (string, required)

Output parameters:

- `architectureQuestions` (array)
- `filename` (string|null)
- `findings` (array)
- `kind` (string|null)
- `language` (string|null)
- `limitation` (string|null)
- `limitations` (array)
- `metrics` (object)
- `sources` (array)
- `summary` (object)
- `truncated` (boolean|null)
- `validated` (boolean|null)

### `dependency_manifest_review` (~80 tokens)

Review a dependency manifest (package.json, requirements.txt, pyproject, go.mod, pom.xml, Gemfile, Cargo.toml as text) for unpinned ranges, git or URL sources, wildcard versions and missing lockfile hints.

Input parameters:

- `content` (string, required)
- `filename` (string, required)
- `lockfilePresent` (boolean)

Output parameters:

- `dependencies` (number|null)
- `filename` (string|null)
- `findings` (array)
- `kind` (string|null)
- `limitation` (string|null)
- `limitations` (array)
- `rules` (array)
- `sources` (array)
- `summary` (object)
- `validated` (boolean|null)

### `requirements_check` (~48 tokens)

Turn a workload brief into explicit requirements, gaps and research questions. No inferred SLA or budget.

Input parameters:

- `constraints` (array, required)
- `requirements` (array, required)
- `workload` (string, required)

Output parameters:

- `constraints` (array)
- `decisionsToClarify` (array)
- `kind` (string|null)
- `limitation` (string|null)
- `nextTools` (array)
- `requirements` (array)
- `sources` (array)
- `validated` (boolean|null)
- `workload` (string|null)

### `architecture_pattern` (~63 tokens)

Select a reference architecture by explicit workload pattern; returns tradeoffs, questions and Mermaid. provider maps the AWS services to Azure, GCP, OCI or open source equivalents.

Input parameters:

- `pattern` (string, required)
- `provider` (string, required)
- `workload` (string, required)

Output parameters:

- `fit` (string|null)
- `kind` (string|null)
- `limitation` (string|null)
- `mermaid` (string|null)
- `nodes` (array)
- `provider` (string|null)
- `questions` (array)
- `serviceMapping` (array)
- `services` (array)
- `sources` (array)
- `tradeoffs` (array)
- `validated` (boolean|null)
- `workload` (string|null)

### `service_compare` (~38 tokens)

Compare curated AWS service families against user constraints. No automatic winner or fabricated scores.

Input parameters:

- `constraints` (array, required)
- `family` (string, required)

Output parameters:

- `constraints` (array)
- `decisionRequired` (string|null)
- `kind` (string|null)
- `limitation` (string|null)
- `options` (array)
- `sources` (array)
- `validated` (boolean|null)

### `decision_record` (~66 tokens)

Generate an ADR from explicit alternatives, decision and consequences. Does not invent acceptance.

Input parameters:

- `consequences` (array, required)
- `context` (string, required)
- `decision` (string, required)
- `options` (array, required)
- `status` (string, required)
- `title` (string, required)

Output parameters:

- `kind` (string|null)
- `limitation` (string|null)
- `markdown` (string|null)
- `sources` (array)
- `validated` (boolean|null)

### `well_architected_review` (~43 tokens)

Organize evidence by six pillars. A met control without evidence is unknown, never certified.

Input parameters:

- `controls` (array, required)
- `workload` (string, required)

Output parameters:

- `controls` (array)
- `kind` (string|null)
- `limitation` (string|null)
- `missingPillars` (array)
- `next` (string|null)
- `sources` (array)
- `summary` (object)
- `validated` (boolean|null)
- `workload` (string|null)

### `threat_model` (~50 tokens)

Create STRIDE review prompts for explicitly supplied assets and trust boundaries. Review aid, not a scanner.

Input parameters:

- `assets` (array, required)
- `boundaries` (array, required)
- `dataClassification` (string, required)

Output parameters:

- `assets` (array)
- `boundaries` (array)
- `dataClassification` (string|null)
- `kind` (string|null)
- `limitation` (string|null)
- `sources` (array)
- `threats` (array)
- `validated` (boolean|null)

### `failure_rehearsal` (~49 tokens)

Design a controlled failure drill with observable success criteria and stop conditions; never executes it.

Input parameters:

- `failure` (string, required)
- `operation` (string, required)
- `target` (string, required)

Output parameters:

- `acceptance` (array)
- `failure` (string|null)
- `kind` (string|null)
- `limitation` (string|null)
- `operation` (string|null)
- `preconditions` (array)
- `sources` (array)
- `steps` (array)
- `target` (string|null)
- `validated` (boolean|null)

### `capacity_plan` (~57 tokens)

Calculate concurrency and daily data volume from explicit traffic assumptions. No service sizing guarantee.

Input parameters:

- `durationMs` (number, required)
- `headroom` (number, required)
- `payloadKB` (number, required)
- `requestsPerSecond` (number, required)

Output parameters:

- `assumptions` (object)
- `averageConcurrency` (number|null)
- `dailyPayloadGB` (number|null)
- `dailyRequests` (number|null)
- `kind` (string|null)
- `limitations` (array)
- `plannedConcurrency` (number|null)

### `cost_model` (~55 tokens)

Calculate an auditable scenario using caller-supplied unit rates and source URLs. Does not guess AWS prices or credit coverage.

Input parameters:

- `contingencyPercent` (number, required)
- `currency` (string, required)
- `items` (array, required)

Output parameters:

- `contingencyPercent` (number|null)
- `creditWarning` (string|null)
- `currency` (string|null)
- `excluded` (array)
- `items` (array)
- `kind` (string|null)
- `subtotal` (number|null)
- `totalWithContingency` (number|null)

### `slo_budget` (~44 tokens)

Calculate an availability error budget for a chosen period.

Input parameters:

- `availabilityPercent` (number, required)
- `periodDays` (integer, required)
- `usedDowntimeMinutes` (number, required)

Output parameters:

- `allowedDowntimeMinutes` (number|null)
- `availabilityPercent` (number|null)
- `exhausted` (boolean|null)
- `kind` (string|null)
- `limitation` (string|null)
- `periodDays` (number|null)
- `remainingMinutes` (number|null)
- `usedDowntimeMinutes` (number|null)

### `migration_plan` (~53 tokens)

Prepare phased discovery, pilot, migration and rollback gates; includes AWS Transform integration discovery.

Input parameters:

- `constraints` (array, required)
- `source` (string, required)
- `strategy` (string, required)
- `target` (string, required)

Output parameters:

- `constraints` (array)
- `integration` (string|null)
- `kind` (string|null)
- `limitation` (string|null)
- `nextTools` (array)
- `phases` (array)
- `source` (string|null)
- `sources` (array)
- `strategy` (string|null)
- `target` (string|null)
- `validated` (boolean|null)

### `architecture_diagram` (~39 tokens)

Build Mermaid from explicit nodes and edges. Sanitizes labels and rejects dangling edges.

Input parameters:

- `edges` (array, required)
- `nodes` (array, required)

Output parameters:

- `limitation` (string|null)
- `mermaid` (string|null)

### `implementation_plan` (~35 tokens)

Turn an architecture decision into a delivery checklist with validation gates.

Input parameters:

- `decision` (string, required)
- `deliverables` (array, required)

Output parameters:

- `decision` (string|null)
- `deliverables` (array)
- `kind` (string|null)
- `limitation` (string|null)
- `sources` (array)
- `stages` (array)
- `validated` (boolean|null)

### `agent_tool_contract` (~61 tokens)

Design a per-operation authorization and recovery contract for an agent tool.

Input parameters:

- `approvalRequired` (boolean, required)
- `maxDurationSeconds` (integer, required)
- `operation` (string, required)
- `resourceScope` (array, required)
- `reversible` (boolean, required)

Output parameters:

- `approvalRequired` (boolean|null)
- `contract` (object)
- `kind` (string|null)
- `limitation` (string|null)
- `maxDurationSeconds` (number|null)
- `operation` (string|null)
- `resourceScope` (array)
- `reversible` (boolean|null)
- `sources` (array)
- `validated` (boolean|null)

### `c4_model` (~81 tokens)

Build C4 context or container diagrams (Mermaid) from explicit people, systems, containers and relations. Validates endpoints; no infrastructure discovery.

Input parameters:

- `containers` (array, required)
- `externalSystems` (array, required)
- `level` (string, required)
- `people` (array, required)
- `relations` (array, required)
- `system` (string, required)

Output parameters:

- `elements` (object)
- `kind` (string|null)
- `level` (string|null)
- `limitation` (string|null)
- `mermaid` (string|null)
- `nextLevel` (string|null)
- `sources` (array)
- `unreferenced` (array)
- `validated` (boolean|null)

### `sequence_diagram` (~57 tokens)

Build a Mermaid sequence diagram from participants and ordered messages, with optional activation, notes and alt/loop blocks. Rejects unknown participants.

Input parameters:

- `messages` (array, required)
- `participants` (array, required)
- `title` (string, required)

Output parameters:

- `kind` (string|null)
- `limitation` (string|null)
- `mermaid` (string|null)
- `messages` (number|null)
- `sources` (array)
- `validated` (boolean|null)

### `service_equivalents` (~76 tokens)

Map a cloud capability to equivalent managed services on AWS, Azure, Google Cloud, OCI and open source. Names as of the snapshot date; verify current naming, regions and pricing before deciding.

Input parameters:

- `categories` (array)
- `from` (string, required)
- `query` (string)
- `to` (array, required)

Output parameters:

- `categories` (array)
- `from` (string|null)
- `kind` (string|null)
- `limitation` (string|null)
- `rows` (array)
- `snapshotDate` (string|null)

### `data_classification` (~67 tokens)

Classify data elements, map them to regulation hints (LGPD, GDPR, PCI DSS, HIPAA) and list handling controls and open questions. Review aid, not legal advice.

Input parameters:

- `elements` (array, required)
- `jurisdictions` (array, required)
- `system` (string, required)

Output parameters:

- `highestSensitivity` (string|null)
- `items` (array)
- `jurisdictions` (array)
- `kind` (string|null)
- `limitation` (string|null)
- `nextTools` (array)
- `sources` (array)
- `summary` (object)
- `system` (string|null)
- `validated` (boolean|null)

### `openapi_review` (~53 tokens)

Heuristic review of an OpenAPI 3.x document (JSON): security, pagination, error responses, idempotency, versioning and documentation gaps. Not a linter replacement.

Input parameters:

- `document` (object, required)

Output parameters:

- `findings` (array)
- `kind` (string|null)
- `limitation` (string|null)
- `limitations` (array)
- `openapi` (string|null)
- `operations` (number|null)
- `paths` (number|null)
- `securitySchemes` (array)
- `sources` (array)
- `summary` (object)
- `validated` (boolean|null)

### `event_contract` (~91 tokens)

Design an event contract: envelope fields, schema evolution rules, idempotency, ordering, DLQ and replay decisions for a named business event. Deterministic template with open questions.

Input parameters:

- `consumers` (array, required)
- `deliveryGuarantee` (string, required)
- `eventName` (string, required)
- `ordering` (string, required)
- `payloadFields` (array, required)
- `producer` (string, required)

Output parameters:

- `consumers` (array)
- `envelope` (string|null)
- `eventName` (string|null)
- `jsonSchema` (object)
- `kind` (string|null)
- `limitation` (string|null)
- `nextTools` (array)
- `rules` (object)
- `sources` (array)
- `validated` (boolean|null)
- `warnings` (array)

### `latency_budget` (~56 tokens)

Split an end-to-end latency objective across hops and show which hops exceed their share. Pure arithmetic over caller-supplied estimates.

Input parameters:

- `hops` (array, required)
- `percentile` (string, required)
- `targetMs` (number, required)

Output parameters:

- `estimatedTotalMs` (number|null)
- `hops` (array)
- `kind` (string|null)
- `limitations` (array)
- `parallelGroups` (object)
- `percentile` (string|null)
- `remainingMs` (number|null)
- `suggestions` (array)
- `targetMs` (number|null)
- `utilizationPercent` (number|null)
- `withinBudget` (boolean|null)

### `queue_sizing` (~101 tokens)

Size consumers with Little's law and stable Erlang C: utilization, wait probability, backlog drain time and target consumers. At most 100,000 total concurrent slots (consumers × concurrency).

Input parameters:

- `arrivalsPerSecond` (number, required)
- `backlogMessages` (number, required)
- `consumers` (integer, required)
- `maxConcurrencyPerConsumer` (integer, required)
- `serviceTimeMs` (number, required)
- `targetUtilizationPercent` (number, required)

Output parameters:

- `backlogDrainSeconds`
- `consumersForTargetUtilization` (number|null)
- `formulas` (array)
- `inputs` (object)
- `kind` (string|null)
- `limitations` (array)
- `meanInSystem`
- `offeredLoadErlangs` (number|null)
- `stable` (boolean|null)
- `totalCapacity` (number|null)
- `utilizationPercent` (number|null)
- `visibilityTimeoutHintSeconds` (number|null)
- `waitProbability` (number|null)
- `warnings` (array)

### `dr_strategy` (~108 tokens)

Compare disaster recovery tiers (backup-and-restore, pilot light, warm standby, active-active) against RTO, RPO and data constraints; returns feasible tiers and required capabilities, not a guarantee.

Input parameters:

- `dataGB` (number, required)
- `regulatoryResidency` (string)
- `replicationBandwidthMbps` (number)
- `rpoMinutes` (number, required)
- `rtoMinutes` (number, required)
- `statefulComponents` (array, required)
- `workload` (string, required)

Output parameters:

- `checks` (array)
- `initialFullCopyHours` (number|null)
- `kind` (string|null)
- `limitation` (string|null)
- `nextTools` (array)
- `objectives` (object)
- `recommendedStartingPoint` (string|null)
- `sources` (array)
- `tiers` (array)
- `validated` (boolean|null)
- `workload` (string|null)

### `retry_policy` (~95 tokens)

Compute an exponential backoff schedule with jitter, the worst-case wait and whether it fits a deadline; adds idempotency and circuit-breaker guidance.

Input parameters:

- `baseDelayMs` (number, required)
- `capMs` (number, required)
- `deadlineMs` (number)
- `factor` (number, required)
- `jitter` (string, required)
- `maxAttempts` (integer, required)
- `operationIdempotent` (boolean, required)

Output parameters:

- `attemptsThatFitDeadline` (number|null)
- `guidance` (array)
- `inputs` (object)
- `kind` (string|null)
- `retriesAfterFirstAttempt` (array)
- `sources` (array)
- `worstCaseWaitMs` (number|null)

### `storage_growth` (~114 tokens)

Project storage volume and relative cost over time from ingest, retention, compression, replication and growth; suggests tiering thresholds.

Input parameters:

- `coldTierPricePerGBMonth` (number)
- `compressionRatio` (number, required)
- `dailyIngestGB` (number, required)
- `hotDays` (integer, required)
- `hotTierPricePerGBMonth` (number)
- `monthlyGrowthPercent` (number, required)
- `months` (integer, required)
- `replicationFactor` (number, required)
- `retentionDays` (integer, required)

Output parameters:

- `assumptions` (object)
- `finalStoredGB` (number|null)
- `finalStoredTB` (number|null)
- `kind` (string|null)
- `limitations` (array)
- `series` (array)
- `steadyState` (boolean|null)
- `tiering` (string|null)

### `finops_unit_economics` (~97 tokens)

Compute cost per unit (request, customer, transaction), fixed versus variable split and the volume at which the marginal cost crosses a target. Caller supplies costs; no provider prices are guessed.

Input parameters:

- `currency` (string, required)
- `fixedCosts` (array, required)
- `period` (string, required)
- `targetCostPerPrimaryUnit` (number)
- `units` (array, required)
- `variableCosts` (array, required)

Output parameters:

- `breakEvenVolumeForTarget` (number|null)
- `currency` (string|null)
- `kind` (string|null)
- `limitations` (array)
- `marginalCostPerPrimaryUnit` (number|null)
- `perUnit` (array)
- `period` (string|null)
- `reading` (array)
- `totals` (object)

### `postmortem` (~131 tokens)

Generate a blameless postmortem document from incident facts: timeline, impact, detection, contributing factors and owned action items. Rejects action items without owner and due date.

Input parameters:

- `actionItems` (array, required)
- `contributingFactors` (array, required)
- `detectedAt` (string, required)
- `impact` (string, required)
- `mitigatedAt` (string, required)
- `resolvedAt` (string, required)
- `severity` (string, required)
- `startedAt` (string, required)
- `timeline` (array, required)
- `title` (string, required)
- `whatWentWell` (array, required)

Output parameters:

- `coverage` (object)
- `kind` (string|null)
- `markdown` (string|null)
- `metrics` (object)
- `warnings` (array)

### `runbook` (~98 tokens)

Generate an operational runbook from service facts: alerts, diagnostic steps, remediation, rollback, escalation and verification. Template with explicit placeholders for what the caller did not provide.

Input parameters:

- `alerts` (array, required)
- `dashboards` (array, required)
- `diagnostics` (array, required)
- `escalation` (array, required)
- `owner` (string, required)
- `remediation` (array, required)
- `rollback` (array, required)
- `service` (string, required)

Output parameters:

- `kind` (string|null)
- `markdown` (string|null)
- `missing` (array)
- `nextTools` (array)

### `agent_eval_plan` (~76 tokens)

Design an evaluation plan for an AI agent: golden set sizing, metrics, judge rubric, red-team cases and regression cadence from explicit capabilities and risks.

Input parameters:

- `agent` (string, required)
- `capabilities` (array, required)
- `releaseCadence` (string, required)
- `risks` (array, required)
- `tools` (array, required)

Output parameters:

- `agent` (string|null)
- `goldenSet` (object)
- `judgeRubric` (array)
- `kind` (string|null)
- `limitation` (string|null)
- `metrics` (array)
- `mutatingTools` (array)
- `nextTools` (array)
- `redTeam` (array)
- `requirements` (array)
- `sources` (array)
- `validated` (boolean|null)

### `prompt_injection_checklist` (~73 tokens)

Enumerate injection paths and controls for an agent from its tools and untrusted data sources; produces a checklist with status to fill, not a scan.

Input parameters:

- `agent` (string, required)
- `humanInLoop` (boolean, required)
- `tools` (array, required)
- `untrustedSources` (array, required)

Output parameters:

- `agent` (string|null)
- `blockers` (array)
- `controls` (array)
- `kind` (string|null)
- `limitation` (string|null)
- `paths` (array)
- `sources` (array)
- `validated` (boolean|null)

### `rag_pipeline_plan` (~85 tokens)

Plan a retrieval-augmented generation pipeline from corpus facts: chunking, embedding, indexing, authorization, evaluation and cost drivers, with open questions. No vendor is chosen for you.

Input parameters:

- `authorization` (string, required)
- `citationsRequired` (boolean, required)
- `corpus` (object, required)
- `latencyBudgetMs` (number, required)
- `useCase` (string, required)

Output parameters:

- `costDrivers` (array)
- `kind` (string|null)
- `limitation` (string|null)
- `nextTools` (array)
- `openQuestions` (array)
- `sizing` (object)
- `sources` (array)
- `stages` (array)
- `useCase` (string|null)
- `validated` (boolean|null)

### `mcp_server_review` (~70 tokens)

Heuristic safety review of ANOTHER MCP server from its tools/list output: tool-poisoning text, missing annotations, risky parameters, free-form schemas, name shadowing and context cost. Paste the JSON your client shows.

Input parameters:

- `serverName` (string, required)
- `tools` (array, required)

Output parameters:

- `approxContextTokens` (number|null)
- `findings` (array)
- `kind` (string|null)
- `limitation` (string|null)
- `limitations` (array)
- `recommendedAllowlist` (array)
- `server` (string|null)
- `sources` (array)
- `summary` (object)
- `tools` (number|null)
- `validated` (boolean|null)
- `verdict` (string|null)

### `mcp_config_review` (~51 tokens)

Review an MCP client configuration JSON (mcpServers map) for unpinned packages, inline secrets, plain HTTP, auto-approved tools and unreviewed enablement.

Input parameters:

- `config` (object, required)

Output parameters:

- `findings` (array)
- `kind` (string|null)
- `limitation` (string|null)
- `limitations` (array)
- `rules` (array)
- `servers` (array)
- `sources` (array)
- `summary` (object)
- `validated` (boolean|null)

### `iam_policy_review` (~61 tokens)

Inspect an IAM document for broad grants: AWS policy JSON (default), Azure custom role definition or Google Cloud IAM policy bindings (provider). Heuristic only; the provider analyzers are authoritative.

Input parameters:

- `policy` (object, required)
- `provider` (string, required)

Output parameters:

- `findings` (array)
- `kind` (string|null)
- `limitation` (string|null)
- `limitations` (array)
- `provider` (string|null)
- `sources` (array)
- `validated` (boolean|null)

### `cloudformation_review` (~37 tokens)

Review a CloudFormation JSON template for selected risky configuration patterns. Intrinsic functions are flagged for human review.

Input parameters:

- `template` (object, required)

Output parameters:

- `findings` (array)
- `kind` (string|null)
- `limitation` (string|null)
- `limitations` (array)
- `resourceCount` (number|null)
- `sources` (array)
- `validated` (boolean|null)

### `terraform_plan_review` (~64 tokens)

Review a Terraform or OpenTofu plan exported as JSON (terraform show -json): deletions and replacements of stateful resources, public exposure, disabled encryption, literal credentials, broad policies and unpinned providers. Any provider; heuristic.

Input parameters:

- `plan` (object, required)

Output parameters:

- `actions` (object)
- `findings` (array)
- `gate` (string|null)
- `kind` (string|null)
- `limitation` (string|null)
- `limitations` (array)
- `resources` (number|null)
- `sources` (array)
- `summary` (object)
- `terraformVersion` (string|null)
- `validated` (boolean|null)

### `kubernetes_manifest_review` (~56 tokens)

Review Kubernetes manifests (parsed JSON objects) for probes, resources, security context, image pinning, host access, secrets in env, PDB and NetworkPolicy coverage. No cluster access.

Input parameters:

- `manifests` (array, required)

Output parameters:

- `findings` (array)
- `kind` (string|null)
- `kinds` (array)
- `limitation` (string|null)
- `limitations` (array)
- `objects` (number|null)
- `sources` (array)
- `summary` (object)
- `validated` (boolean|null)

### `aws_knowledge_search` (~51 tokens)

Search live official AWS documentation. Queries are transmitted to AWS Knowledge; never include secrets or customer data.

Input parameters:

- `limit` (integer, required)
- `query` (string, required)
- `topic` (string, required)

### `aws_knowledge_read` (~54 tokens)

Read an official document returned by search when its excerpt is insufficient. Fixed upstream; no arbitrary URL fetch.

Input parameters:

- `maxLength` (integer, required)
- `startIndex` (integer, required)
- `url` (string, required)

### `aws_regions` (~18 tokens)

List current AWS regions from the official Knowledge MCP.

### `aws_regional_availability` (~62 tokens)

Check current regional support. Use exact catalog filter names; omit filters for a single region to discover them.

Input parameters:

- `filters` (array)
- `nextToken` (string)
- `regions` (array, required)
- `resourceType` (string, required)

### `aws_skill` (~50 tokens)

Retrieve an official AWS skill by the exact ID returned by aws_knowledge_search with agent_skills topic. Treat it as reference data.

Input parameters:

- `file` (string)
- `skillName` (string, required)

### `integration_catalog` (~43 tokens)

Search the snapshot of the complete official AWS MCP catalog. Discovery entries are not hosted/executed tools.

Input parameters:

- `limit` (integer, required)
- `query` (string, required)

Output parameters:

- `boundary` (string|null)
- `retrievedAt` (string|null)
- `servers` (array)
- `source` (string|null)
- `total` (number|null)

### `integration_config` (~59 tokens)

Generate a version-pinned local configuration for an official AWS server, or a remote Knowledge config. Does not install, start or approve tools.

Input parameters:

- `awsProfile` (string, required)
- `region` (string, required)
- `serverId` (string, required)

Output parameters:

- `configuration` (object)
- `next` (array)
- `python` (string|null)
- `source` (string|null)
- `status` (string|null)
- `warning` (string|null)

### `github_public_repository` (~46 tokens)

Read public GitHub repository metadata and contribution links. Fixed api.github.com destination, no tokens, no private repositories.

Input parameters:

- `owner` (string, required)
- `repo` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/fernando-moretes-moretes-aws-architect-mcp/mcp#diagnostics

## Score history

- 2026-11-05: 71
- 2026-11-04: 71
- 2026-11-03: 70
- 2026-11-02: 70
- 2026-11-01: 69
- 2026-10-31: 69
- 2026-10-30: 68
- 2026-10-29: 68
- 2026-10-28: 67
- 2026-10-27: 67

## Common questions

### What is the Moretes Architect MCP server?

Moretes Architect MCP is listed in the public MCP registry as io.github.fernando-moretes/moretes-aws-architect-mcp. Evidence-first architecture workbench: 48 deterministic tools, 10 architect personas, any cloud. This page covers its hosted endpoint (https://mcp.moretes.com/mcp).

### Is the Moretes Architect MCP server safe to use?

Moretes Architect MCP scores 71 out of 100 on VerifyMCP. 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 Moretes Architect MCP server expose?

Moretes Architect MCP exposes 48 tools: architect_panel, code_review_architecture, dependency_manifest_review, requirements_check, architecture_pattern, and 43 more. Their descriptions and schemas cost roughly 3,134 tokens of context every time the server is loaded.

### Does the Moretes Architect MCP server require authentication?

No. We connected to Moretes Architect MCP without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Moretes Architect MCP server still maintained?

Moretes Architect MCP is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.moretes.com/mcp
- Repository: https://github.com/fernando-moretes/moretes-aws-architect-mcp
- Website: https://fernando.moretes.com/mcp
- Changelog RSS feed: https://verifymcp.io/servers/fernando-moretes-moretes-aws-architect-mcp/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/fernando-moretes-moretes-aws-architect-mcp/mcp.json
- HTML version of this page: https://verifymcp.io/servers/fernando-moretes-moretes-aws-architect-mcp/mcp