# Cloudeval AI (npm · @ganakailabs/cloudeval-cli)

Cloud evaluations and reviews for Azure and static AWS CloudFormation (beta). Requires an account.

- Trust score: 83/100 (high trust)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- npm · `@ganakailabs/cloudeval-cli`: 83/100 (this document), [markdown](https://verifymcp.io/servers/ganakailabs-cloudeval/ganakailabs-cloudeval-cli.md), [page](https://verifymcp.io/servers/ganakailabs-cloudeval/ganakailabs-cloudeval-cli)

## Channel facts

- Registry: `npm`
- Package: `@ganakailabs/cloudeval-cli`
- Version: `0.38.5`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-20.

- **Supply Chain Security**: 99/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 65 of 264 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 87/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to ganakailabs/cloudeval-cli).
  - License check failed: the license (LicenseRef-CloudEval-CLI) isn't a recognized OSI-approved license.
  - Actively maintained (last published 10 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 78/100
  - 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 6918 tokens (~135/item across 51 items; 45 tools + 6 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 37/100
  - Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 92% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 45 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 47 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the Cloudeval AI MCP server?

Cloudeval AI runs locally as an npm package, launched with npx -y @ganakailabs/cloudeval-cli. 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 ganakailabs-cloudeval -- npx -y @ganakailabs/cloudeval-cli
```

### Cursor

```json
{
  "mcpServers": {
    "ganakailabs-cloudeval": {
      "command": "npx",
      "args": [
        "-y",
        "@ganakailabs/cloudeval-cli"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ganakailabs-cloudeval": {
      "command": "npx",
      "args": [
        "-y",
        "@ganakailabs/cloudeval-cli"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add ganakailabs-cloudeval -- npx -y @ganakailabs/cloudeval-cli
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ganakailabs-cloudeval": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@ganakailabs/cloudeval-cli"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ganakailabs-cloudeval --command npx --arg -y --arg @ganakailabs/cloudeval-cli
```

### Hermes

```yaml
mcp_servers:
  ganakailabs-cloudeval:
    command: "npx"
    args: ["-y", "@ganakailabs/cloudeval-cli"]
```

### Netclaw

```json
{
  "McpServers": {
    "ganakailabs-cloudeval": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@ganakailabs/cloudeval-cli"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add ganakailabs-cloudeval -t stdio -c npx -a -y @ganakailabs/cloudeval-cli
```

### Other

```json
{
  "mcpServers": {
    "ganakailabs-cloudeval": {
      "command": "npx",
      "args": [
        "-y",
        "@ganakailabs/cloudeval-cli"
      ]
    }
  }
}
```

## 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.

### 2026-09-20 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-18 (score 82, +5)

- [functional improvement] Stability: unverified → 0.30

### 2026-09-09 (score 77)

First indexed and scored.

## MCP tools (45)

### `capabilities_get` (~127 tokens)

Get Cloudeval Capabilities

Return Cloudeval CLI and MCP capability metadata for agent planning.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `agent_profiles_list` (~139 tokens)

List Agent Profiles

List backend-owned Cloudeval Agent Profiles such as Architecture, Cost, Change Reviewer, Evidence Auditor, and Security Reviewer.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `agent_profiles_get` (~140 tokens)

Get Agent Profile

Fetch one Cloudeval Agent Profile by id.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.
- `profileId` (string, required): Agent Profile id, for example cost.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `projects_list` (~125 tokens)

List Projects

List Cloudeval projects visible to the authenticated account.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `projects_get` (~145 tokens)

Get Project

Fetch one Cloudeval project by id from the authenticated account's project list.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.
- `projectId` (string, required): Cloudeval project id to fetch.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `projects_overview` (~165 tokens)

Get Project Overview

Fetch a Cloudeval project cockpit overview with graph, report, connection, credit, and deep-link metadata for IDE and agent workflows.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.
- `projectId` (string): Cloudeval project id to inspect. Defaults to the configured project when omitted.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `projects_graph_get` (~183 tokens)

Get Project Graph

Fetch project graph nodes and relationships for automation.

Input parameters:

- `asOf` (string): Optional replay timestamp.
- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `includeDiff` (boolean)
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.
- `projectId` (string): Cloudeval project id. Defaults to active profile defaultProjectId, then Playground/first project where supported.
- `syncVersion` (string): Optional sync version.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `projects_graph_timeline` (~160 tokens)

Project Graph Timeline

List retained graph snapshots for a project.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `limit` (number)
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.
- `projectId` (string): Cloudeval project id. Defaults to active profile defaultProjectId, then Playground/first project where supported.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `projects_graph_diff` (~176 tokens)

Project Graph Diff

Compare two retained project graph snapshots.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `fromSyncVersion` (string): Baseline sync version.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.
- `projectId` (string): Cloudeval project id. Defaults to active profile defaultProjectId, then Playground/first project where supported.
- `toSyncVersion` (string): Target sync version.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `projects_graph_insights` (~201 tokens)

Project Graph Insights

Fetch graph intelligence for overview, impact, critical paths, security, cost, or changes.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `focus` (string)
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `limit` (number)
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.
- `projectId` (string): Cloudeval project id. Defaults to active profile defaultProjectId, then Playground/first project where supported.
- `resourceId` (string): Resource id for impact analysis.
- `syncVersion` (string): Optional sync version.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `projects_graph_sync_runs` (~162 tokens)

Project Graph Sync Runs

List recent graph-producing sync runs for a project.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `limit` (number)
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.
- `projectId` (string): Cloudeval project id. Defaults to active profile defaultProjectId, then Playground/first project where supported.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `connections_list` (~127 tokens)

List Connections

List Cloudeval cloud/template connections visible to the authenticated account.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `connections_get` (~145 tokens)

Get Connection

Fetch one Cloudeval connection by id from the authenticated account's connection list.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `connectionId` (string, required): Cloudeval connection id to fetch.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `reports_list` (~165 tokens)

List Reports

List cost and Well-Architected reports for a project.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `kind` (string): Report kind filter.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.
- `projectId` (string): Cloudeval project id. Defaults to active profile defaultProjectId, then Playground/first project where supported.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `reports_show` (~175 tokens)

Show Report

Fetch one Cloudeval report by id for a project.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.
- `projectId` (string): Cloudeval project id. Defaults to active profile defaultProjectId, then Playground/first project where supported.
- `reportId` (string, required): Cloudeval report id.
- `view` (string)

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `reports_cost` (~178 tokens)

Latest Cost Report

Fetch the latest normalized Cloudeval cost report for a project.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `period` (string)
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.
- `projectId` (string): Cloudeval project id. Defaults to active profile defaultProjectId, then Playground/first project where supported.
- `view` (string): Cost view hint such as overview or raw.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `reports_waf` (~197 tokens)

Latest WAF Report

Fetch the latest normalized Well-Architected report for a project.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.
- `projectId` (string): Cloudeval project id. Defaults to active profile defaultProjectId, then Playground/first project where supported.
- `reportId` (string): Optional report id.
- `severity` (string): Optional severity filter.
- `view` (string): WAF view hint such as overview, rules, or raw.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `reports_rules` (~168 tokens)

WAF Rules

Return WAF rule findings from the latest Cloudeval WAF report.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.
- `projectId` (string): Cloudeval project id. Defaults to active profile defaultProjectId, then Playground/first project where supported.
- `severity` (string): Optional severity filter.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `rules_categories` (~120 tokens)

Rule Categories

List cloud validation check categories.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `rules_search` (~147 tokens)

Search Rules

Search cloud validation checks.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `category` (string): Category filter.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `pillar` (string): Architecture pillar filter.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.
- `query` (string, required): Search query.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `rules_get` (~133 tokens)

Get Rule

Show one cloud validation check by id.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.
- `ruleId` (string, required): Validation check id.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `billing_summary` (~128 tokens)

Billing Summary

Return Cloudeval billing entitlement, credit status, and subscription status.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `billing_usage` (~196 tokens)

Billing Usage

Return Cloudeval billing usage summary with date, granularity, and model filters.

Input parameters:

- `actionType` (string)
- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `chargeStatus` (string)
- `endAt` (string): End timestamp.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `granularity` (string)
- `model` (string)
- `outcome` (string)
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.
- `range` (string)
- `startAt` (string): Start timestamp.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `billing_ledger` (~415 tokens)

Billing Ledger

Inspect individual Cloudeval usage attempts and credit charges for the authenticated account. Use billing_usage for aggregates or billing_invoices for payment receipts. Defaults to the last 30 calendar days; explicit timestamps override the corresponding range bounds. Returns data.items, data.has_more and data.next_cursor; reuse the cursor with the same filters to read the next page. Requires billing read access; does not initiate purchases or evaluations.

Input parameters:

- `actionType` (string): Exact action_type value from a ledger row. Omit to include all action types.
- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `chargeStatus` (string): Charge disposition filter: charged, not_charged or bypassed.
- `cursor` (string): Opaque data.next_cursor from the previous response. Omit for the first page; retain the same filters while paging.
- `endAt` (string): Exclusive ISO 8601 upper bound; overrides the range end.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `limit` (number): Page size; the MCP handler floors and clamps it to 1–100.
- `model` (string): Exact model_name or operation value from a ledger row. Omit to include all models.
- `outcome` (string): Usage outcome filter, such as success, failure, blocked or skipped.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.
- `range` (string): Calendar-day window ending now. Use all for no implicit date bounds.
- `startAt` (string): Inclusive ISO 8601 lower bound, for example 2026-09-01T00:00:00Z; overrides the range start.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `billing_plans` (~123 tokens)

Billing Plans

Return Cloudeval billing plan configuration.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `billing_topups` (~125 tokens)

Billing Top-ups

Return available Cloudeval credit top-up packs.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `billing_notifications` (~132 tokens)

Billing Notifications

Return Cloudeval billing notifications for the authenticated account.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `limit` (number)
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `models_list` (~129 tokens)

List Models

List backend-supported Cloudeval models for the active account or access key.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `models_default_get` (~126 tokens)

Get Default Model

Return the configured default model for the selected CLI profile.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `sessions_list` (~131 tokens)

List Sessions

List local Cloudeval CLI session history summaries.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `limit` (number)
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `sessions_get` (~138 tokens)

Get Session

Return one local Cloudeval CLI session by thread id.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.
- `threadId` (string, required): Local session thread id.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `sessions_search` (~141 tokens)

Search Sessions

Search local Cloudeval CLI session titles and messages.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `limit` (number)
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.
- `query` (string, required): Search query.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `sessions_export` (~127 tokens)

Export Sessions

Return local Cloudeval CLI session history for the selected profile.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `identity_get` (~127 tokens)

Get Identity

Return Cloudeval identity and capability metadata for the active credential.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `auth_status` (~122 tokens)

Auth Status

Return local Cloudeval authentication status.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `status` (~125 tokens)

CLI Status

Return local Cloudeval CLI status and active configuration metadata.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `doctor` (~150 tokens)

CLI Doctor

Return local Cloudeval CLI diagnostic checks.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `deep` (boolean): Check backend reachability as well as local setup.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `mcp` (boolean): Include MCP metadata checks.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `config_show` (~124 tokens)

Show Config

Return the selected Cloudeval CLI profile configuration.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `config_get` (~135 tokens)

Get Config Value

Return one setting from the selected Cloudeval CLI profile.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `key` (string, required): Config key.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `config_profiles` (~123 tokens)

List Config Profiles

Return Cloudeval CLI config profile names.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `credentials_templates` (~123 tokens)

Credential Templates

List Cloudeval access-key credential templates.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `credentials_list` (~156 tokens)

List Credentials

List Cloudeval access-key credentials, optionally scoped by project.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.
- `projectId` (string): Cloudeval project id. Defaults to active profile defaultProjectId, then Playground/first project where supported.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `credentials_inspect` (~136 tokens)

Inspect Credential

Inspect a Cloudeval access-key credential by id.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `credentialId` (string, required): Credential id.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `recipes_list` (~125 tokens)

List Recipes

List Cloudeval reusable recipes and their safety metadata.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

### `recipes_get` (~136 tokens)

Get Recipe

Fetch one Cloudeval recipe by id.

Input parameters:

- `baseUrl` (string): Cloudeval API base URL. Defaults to the MCP server --base-url, active profile, CLOUDEVAL_BASE_URL, or the public API.
- `frontendUrl` (string): Cloudeval frontend base URL for generated links. Defaults to --frontend-url, active profile, CLOUDEVAL_FRONTEND_URL, or public frontend.
- `profile` (string): Cloudeval CLI config profile to read defaults from. Defaults to the server --profile or CLOUDEVAL_PROFILE.
- `recipeId` (string, required): Cloudeval recipe id.

Output parameters:

- `command` (string)
- `data`: Tool-specific result payload.
- `filesWritten` (array)
- `frontendUrl` (string)
- `ok` (boolean)
- `traceId` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/ganakailabs-cloudeval/ganakailabs-cloudeval-cli#diagnostics

## Score history

- 2026-09-20: 83
- 2026-09-19: 82
- 2026-09-18: 82
- 2026-09-17: 77
- 2026-09-16: 77
- 2026-09-15: 77
- 2026-09-14: 77
- 2026-09-13: 77
- 2026-09-12: 77
- 2026-09-11: 77
- 2026-09-10: 77
- 2026-09-09: 77

## Common questions

### What is the Cloudeval AI MCP server?

Cloudeval AI is an MCP server listed in the public MCP registry as io.github.ganakailabs/cloudeval. Cloud evaluations and reviews for Azure and static AWS CloudFormation (beta). Requires an account. This page covers its npm package (@ganakailabs/cloudeval-cli).

### Is the Cloudeval AI MCP server safe to use?

Cloudeval AI scores 83 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 Cloudeval AI MCP server expose?

Cloudeval AI exposes 45 tools: capabilities_get, agent_profiles_list, agent_profiles_get, projects_list, projects_get, and 40 more. Their descriptions and schemas cost roughly 6,771 tokens of context every time the server is loaded.

### Is the Cloudeval AI MCP server still maintained?

Cloudeval AI is still listed as active in the MCP registry. We last reached this channel on 20 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 Cloudeval AI MCP server under?

Cloudeval AI declares the LicenseRef-CloudEval-CLI licence, which is not on the OSI-approved list. Read the terms before using it at work, and note this covers the source only, not the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@ganakailabs/cloudeval-cli
- Socket report: https://socket.dev/npm/package/@ganakailabs/cloudeval-cli
- Repository: https://github.com/ganakailabs/cloudeval-cli
- Website: https://docs.cloudeval.ai/agents/mcp-client-setup
- Changelog RSS feed: https://verifymcp.io/servers/ganakailabs-cloudeval/ganakailabs-cloudeval-cli.xml
- Changelog JSON feed: https://verifymcp.io/servers/ganakailabs-cloudeval/ganakailabs-cloudeval-cli.json
- HTML version of this page: https://verifymcp.io/servers/ganakailabs-cloudeval/ganakailabs-cloudeval-cli