Server providing Argo CD integration for MCP clients.
Nothing to run from here
Luno CMS is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
trust score
42
downloads a day
local
runs on your machine
1k
downloads in 30d
What it does
LUNO — AI-era Backend Platform (not Luno crypto). BUILD/OPERATE, REGISTER/GOVERN, CONSUME.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'LUNO_API_URL=${LUNO_API_URL}' --env 'LUNO_AGENT_KEY=${LUNO_AGENT_KEY}' --transport stdio luno-cms-mcp '--' npx -y @luno-cms/mcp
# 2 — ask your agent for something these tools do
# get_tenant_schema, get_project_overview, list_form_sets and 49 more
It needs LUNO_API_URL, LUNO_AGENT_KEY: this reads them from your environment, so export them first.
Luno CMS costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
LCAll 1 server
luno-cms1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Luno CMS as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads LUNO_API_URL (LUNO admin API base URL, e.g. https://api.luno.rest/admin), LUNO_AGENT_KEY (Required secret. Agent API key (sk-agent-…) from LUNO Console → MCP / API / Hook → API / MCP) from your environment each time it starts the server, so the value stays out of its config: export them in your shell profile (macOS, Linux), or run setx LUNO_API_URL …, setx LUNO_AGENT_KEY … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'LUNO_API_URL=${LUNO_API_URL}' --env 'LUNO_AGENT_KEY=${LUNO_AGENT_KEY}' --transport stdio luno-cms-mcp '--' npx -y @luno-cms/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: LUNO_API_URL — LUNO admin API base URL, e.g. https://api.luno.rest/admin; LUNO_AGENT_KEY — Required secret. Agent API key (sk-agent-…) from LUNO Console → MCP / API / Hook → API / MCP. You set them in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
52 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
操作中プロジェクトのフォームセット・フィールド定義を一括取得する。引数なし。
No parameter schema on file.
既存プロジェクト再開時の最初の一手。intentCapabilities（ユーザー意図→プロダクト。お問い合わせは create_contact_form。お知らせ/ブログは purposeLabels で templateSlug）・nextMoves・hints.intent・Form Sets・Contact Forms・Masters・quota・locales・公開 API ベースを返す。空プロジェクトでも Contact を Form Set テンプレに落とさない。権限不足は available:false。詳細: agent.discover。引数なし。
No parameter schema on file.
Form Set 一覧を取得する。引数なし。各 item の id（UUID）を他ツールの formSetId に使う（slug ではない）。
No parameter schema on file.
1 つの Form Set のスキーマ + save_revision 用 snapshotShape。select/radio/multiselect には masterEntityKey・sampleValues・公開 records URL を付与。保存前に必ず確認する。必須: formSetId（UUID。Form Set の slug ではない。list_form_sets / apply_* の id）。
No parameter schema on file.
エージェントキーのプロジェクト向け公開 API ベース URL を返す。引数なし。ローカルでは /public/p/{projectId}/v1 を使う（Host ベース /public/v1 は DEFAULT_TENANT_ID に落ちる）。
No parameter schema on file.
Form Set 内のエントリ一覧。必須: formSetId（UUID）。返却 item.id を entryId に使う。
No parameter schema on file.
エントリ 1 件。必須: formSetId, entryId（いずれも UUID）。
No parameter schema on file.
エントリを新規作成（本文は含めない。続けて save_revision → get_pub_preview_url → publish_revision）。必須: formSetId（UUID）, slug（エントリの URL スラッグ）。任意: idempotencyKey（同一キー再送で同じ id）。返却 id を entryId に使う。
No parameter schema on file.
Form Set 内にエントリを最大 50 件一括作成（slug のみ。本文は save_revision）。必須: formSetId, items[{ slug }]。任意: idempotencyKey（バッチ全体の冪等リプレイ）。各 item は独立に成功/失敗（slug 衝突は当該 item のみ failed）。N×create_entry の代わりに 1 ツールコール。削除の一括は不可（agent.mcp-security-permissions）。
No parameter schema on file.
エントリの slug を更新。必須: formSetId, entryId, slug。
No parameter schema on file.
指定リビジョンを承認申請する（公開まで一括したい場合は publish_revision を優先）。必須: formSetId, entryId, revisionRowId（= save_revision の id）, revision（= save_revision の revision）。
No parameter schema on file.
アップロード済みメディア（アセット）一覧。任意: limit（1–100、既定 30）。
No parameter schema on file.
メディアライブラリへ画像/ファイルをアップロード（POST /v1/media）。必須（いずれか一方）: sourceUrl / base64 / filePath（ローカルパス推奨）。任意: filename, mimeType, folderId。返却 id（UUID）を image / image_gallery に入れる（luno://content/schema-guide）。外部 URL を snapshot に直書きしない。stg/prod へローカル画像を上げるときは filePath（sourceUrl の 127.0.0.1 は届かない）。
No parameter schema on file.
エントリのリビジョン一覧。必須: formSetId, entryId。各 item の id / revision を publish_revision に渡す。
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
エージェントタスクの Run を開始（schema/full）。必須: goal。任意: clientLabel（cursor / claude-code / mcp 等）。返却 agentRun.id を以降のツール呼び出しに X-Agent-Run-Id として自動付与（本 MCP セッション内）。詳細: settings.agent-activity / agent.mcp-security-permissions
No parameter schema on file.
Agent Run を終了（schema/full）。必須: runId, status（completed / failed / cancelled）。start_agent_run の agentRun.id を渡す。メトリクス（auditLogCount 等）を返す。
No parameter schema on file.
Agent Run の状態・メトリクスを取得（schema/full）。必須: runId。自分が開始した run のみ（他キーは 403）。
No parameter schema on file.
Change Plan の状態を取得（schema/full）。必須: planId（propose_change の changePlan.id）。自分が提案した plan のみ。承認・却下・実行は Human Console のみ。
No parameter schema on file.
LUNO 公式 Form Set スターター一覧（引数なし）。purposeLabels（ja/en。お知らせ・ブログ等）で用途をマッチし、返却 slug を apply_builtin_form_template の templateSlug に使う。slug を暗記しない。お問い合わせはここに無い。create_contact_form / get_project_overview.intentCapabilities を使う。詳細: agent.builtin-form-templates
No parameter schema on file.
No parameter schema on file.
Master Blueprint を検証（schema/full）。必須: entities（1 件以上の配列）。各 entity: key, name, records[{ value, label, sort_order }]。適用はしない。詳細: agent.master-blueprint-mcp, luno://content/schema-guide。
No parameter schema on file.
Master Blueprint を一括 upsert（schema/full）。必須: entities。任意: dryRun, publish（true でサイトに反映し公開マスタ API に載る。省略時は未反映）。各 record の並びは sort_order / sortOrder。エージェントキーでは update_master_record 不可のためここで正しい sort_order を渡す。詳細: agent.master-blueprint-mcp, luno://content/schema-guide
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
Contact Form を更新（PUT・schema/full。GET した全フィールドを body に含める）。必須: formId（Contact Form UUID）, slug, name, recipient_email, fields。任意: autoreply_*, email_signature。fields は { key, type, label:{ja,en}, required }[]（Form Set の fieldKey ではない）。詳細: agent.contact-form-mcp。
No parameter schema on file.
マスタエンティティ一覧（引数なし。key / hierarchical / record_count 含む）。item.id を entityId に使う。
No parameter schema on file.
マスタエンティティ 1 件。必須: entityId（UUID。list_master_entities の id）。
No parameter schema on file.
マスタレコード一覧（label は locale map。階層時は parent_record_id）。必須: entityId。任意: q（検索）。
No parameter schema on file.
マスタレコードを新規作成（content 可）。必須: entityId, label（string または locale map）。任意: value, sortOrder, parentRecordId, data。並びの一括投入は apply_master_blueprint 推奨。
No parameter schema on file.
マスタレコードを更新。必須: entityId, recordId。任意: label, value, sortOrder, parentRecordId, data。エージェント API キーでは不可（401 — ユーザ JWT + 編集権限が必要）。identifier（slug / value）の変更は rename_master_record_slug → propose_change。並び替えは apply_master_blueprint の sort_order を使う。
No parameter schema on file.
階層マスタの親子・並び順を一括更新。必須: entityId, updates（全レコードを含める配列。各要素に id, parent_record_id, sort_order）。エージェントキーでは 403。
No parameter schema on file.
ヘルプ KB 検索。必須: q。任意: locale（ja|en）, limit（既定 20）。category agent（snapshot / Form Blueprint / 公開 API / publish_revision）もヒット。
No parameter schema on file.
管理画面ヘルプ記事 1 件の本文。必須: articleId（search_admin_help の id。例: content.publish-workflow, agent.publish-revision）。
No parameter schema on file.
LUNO の使い方を自然言語で質問（RAG）。必須: question。任意: locale。snapshot / 公開 API / Blueprint は category agent を参照。
No parameter schema on file.
管理画面ログイン用ブランド取得（認証不要）。任意: projectId（省略時はエージェントキーのプロジェクト）。branding_tier / login_background / hide_* を返す。
No parameter schema on file.
管理画面ログインの見た目設定を取得（認証要・引数なし）。背景=Standard+、WL=Business+。
No parameter schema on file.
管理画面ログインの見た目を更新。任意（1 つ以上推奨）: adminLoginBackground（cosmic|gradient|plain|none・Standard+）, adminLoginHideLunoLogo, adminLoginHidePoweredBy（Business+）。
No parameter schema on file.
管理画面ログイン IP 許可リスト一覧（Business+・引数なし）。
No parameter schema on file.
管理画面ログイン IP 許可ルールを追加（Business+・tenant スコープ）。必須: projectId（プロジェクト UUID）, cidr。
No parameter schema on file.
管理画面ログイン IP 許可ルールを削除（Business+）。必須: ruleId（list_console_login_ip_allowlists の id）。
No parameter schema on file.
サイトのコンテンツ多言語設定を取得（引数なし）。有効/無効・content_locales・content_default_locale。
No parameter schema on file.
サイトのコンテンツ多言語設定を更新（tenant_admin JWT のみ。エージェントキー不可）。任意: contentLocalesEnabled, contentDefaultLocale, contentLocales。
No parameter schema on file.
text/textarea/tiptap をソース言語から他ロケールへ AI 翻訳（Standard+・AI チケット 1/回）。必須: sourceLocale, targetLocales（1–3）, fields（各 formKey/fieldKey/type/sourceText）。返却 items を snapshot にマージして save_revision。
No parameter schema on file.
MCP Private Beta 計測ファネルを再構成。任意: funnelId（省略時は当セッション / LUNO_FUNNEL_ID）。詳細: agent.measurement-funnel
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Luno CMS or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 93 / 100
Release 0.2.51 · scanned 14 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings2 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest6ec2ea0268befe3ca22abbe2e8f72a96a15a022ea8c0eb106b9bab2a9c817b5c
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (52 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_tenant_schema | no tags | |
| get_project_overview | no tags | |
| get_mcp_runtime | no tags | |
| list_form_sets | no tags | |
| get_form_set_schema | no tags | |
| get_public_api_info | no tags | |
| list_entries | no tags | |
| get_entry | no tags | |
| create_entry | no tags | |
| bulk_create_entries | no tags | |
| update_entry | no tags | |
| submit_entry_for_review | no tags | |
| list_media | no tags | |
| upload_media | no tags | |
| list_revisions | no tags | |
| get_pub_preview_url | no tags | |
| save_revision | no tags | |
| apply_form_blueprint | no tags | |
| archive_form_set | no tags | |
| propose_change | no tags | |
| start_agent_run | no tags | |
| end_agent_run | no tags | |
| get_agent_run | no tags | |
| get_change_plan | no tags | |
| list_builtin_form_templates | no tags | |
| apply_builtin_form_template | no tags | |
| validate_master_blueprint | no tags | |
| apply_master_blueprint | no tags | |
| migrate_field_to_master_reference | no tags | |
| rename_master_record_slug | no tags | |
| create_contact_form | external-sink | external-sink: parameter "recipient" |
| update_contact_form | external-sink | external-sink: parameter "recipient" |
| list_master_entities | no tags | |
| get_master_entity | no tags | |
| list_master_records | no tags | |
| create_master_record | no tags | |
| update_master_record | no tags | |
| update_master_tree | no tags | |
| search_admin_help | no tags | |
| get_admin_help_article | no tags | |
| ask_admin_help | no tags | |
| get_login_branding | no tags | |
| get_login_appearance | no tags | |
| update_login_appearance | no tags | |
| list_console_login_ip_allowlists | no tags | |
| add_console_login_ip_allowlist | no tags | |
| delete_console_login_ip_allowlist | no tags | |
| get_project_content_locales | no tags | |
| patch_project_content_locales | no tags | |
| translate_entry_locales | no tags | |
| get_funnel_status | no tags | |
| publish_revision | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest6ec2ea0268befe3c
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.2.51. Pin a release below and the command asks for exactly that one.
0.2.51
22 Sep 2026
latestNo release note was published with this version.
0.2.50
12 Sep 2026
No release note was published with this version.
0.2.46
6 Sep 2026
No release note was published with this version.
0.2.44
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Luno CMS can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.