Provider-neutral MCP server for AgentDispatch.
Free
Nothing to run from here
Cloudron 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.
Open Installation—
p95 latency
—
call success
local
runs on your machine
—
calls last 7d
What it does
MCP server for Cloudron instance management - list apps, get status, and manage your self-hosted applications
Quickstart
# 1 — run it from where its publisher ships it
npx -y @serenichron/mcp-cloudron
# 2 — ask your agent something
> MCP server for Cloudron instance management - list apps, get status, and manage your self-hosted applications
Cloudron is free: there is no plan to choose, no cap to set and nothing that can bill you.
Publishernot claimed
SEAll 1 server
@serenichron1 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 Cloudron 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. It is scanned, signed and pinned to the version you choose — 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. Claude Code registers it in one command.
claude mcp add cloudron-mcp -- npx -y @serenichron/mcp-cloudronReconnect, or start a new session, and the tools appear in the model’s tool list.
Free to install, and it runs from its publisher’s own package: no account, no key, no card.
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
36 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.
List all installed applications on the Cloudron instance. Returns app details including name, domain, status, and health.
Takes no parameters.
Example callreturns →
Get detailed information about a specific application by its ID.
Takes no parameters.
Example callreturns →
Get the current status and configuration of the Cloudron instance.
Takes no parameters.
Example callreturns →
Get the status of an async operation (backup, install, restore, etc.) by task ID. Returns state (pending/running/success/error/cancelled), progress (0-100%), and message.
Takes no parameters.
Example callreturns →
Cancel a running async operation (kill switch). Returns updated task status with state
Takes no parameters.
Example callreturns →
Check available disk space before operations that create data (backup, install). Returns available/total/used disk space in MB, plus warning and critical threshold alerts.
Takes no parameters.
Example callreturns →
Pre-flight validation for destructive operations (uninstall app, delete user, restore backup). Returns validation result with blocking errors, warnings, and recommendations.
Takes no parameters.
Example callreturns →
Control app lifecycle (start, stop, restart). Returns 202 Accepted with task ID for async operation tracking via cloudron_task_status.
Takes no parameters.
Example callreturns →
Update application configuration including environment variables, memory limits, and access control settings. Returns 200 OK with updated app config and restart requirement flag.
Takes no parameters.
Example callreturns →
List all backups available on the Cloudron instance. Returns backup details including ID, timestamp, size, app count, and status. Backups are sorted by timestamp (newest first).
Takes no parameters.
Example callreturns →
Create a new backup of the Cloudron instance. Performs F36 pre-flight storage check (requires 5GB minimum). Returns task ID for tracking backup progress via cloudron_task_status (F34).
Takes no parameters.
Example callreturns →
List all users on the Cloudron instance. Returns user details including ID, email, username, role, and creation date. Users are sorted by role (admin, user, guest) then email.
Takes no parameters.
Example callreturns →
Search the Cloudron App Store for available applications. Returns app details including name, description, version, icon URL, and install count. Results are sorted by relevance score. Empty query returns all available apps.
Takes no parameters.
Example callreturns →
Validate app manifest before installation (pre-flight safety check). Checks storage sufficiency via F36, dependency availability, and manifest schema validity. Returns validation report with errors and warnings.
Takes no parameters.
Example callreturns →
Create a new user on the Cloudron instance with email, password, and role in a single atomic operation. Password must be at least 8 characters long and contain at least 1 uppercase letter and 1 number. Returns 201 Created with user object.
Takes no parameters.
Example callreturns →
Get detailed information about a specific user by user ID. Returns user object with email, username, display name, role, groups, and timestamps.
Takes no parameters.
Example callreturns →
Update an existing user\
Takes no parameters.
Example callreturns →
Delete a user from the Cloudron instance. WARNING: This is a destructive operation. Use cloudron_validate_operation before deletion to check for potential issues (last admin, owned apps). Requires confirmation flag set to true.
Takes no parameters.
Example callreturns →
List all configured domains on the Cloudron instance. Returns domain details including name, provider, verification status, and TLS configuration.
Takes no parameters.
Example callreturns →
Get logs for an app or service. Logs are formatted with timestamps and severity levels for readability. Type parameter determines endpoint:
Takes no parameters.
Example callreturns →
Uninstall an application with pre-flight safety validation. DESTRUCTIVE OPERATION. First validates via cloudron_validate_operation (checks app exists, no dependencies, backup recommended), then calls DELETE /api/v1/apps/:id. Returns 202 Accepted with task ID for async operation tracking.
Takes no parameters.
Example callreturns →
Install application from Cloudron App Store with pre-flight validation. Calls F23a (cloudron_validate_manifest) to verify app exists and F36 (cloudron_check_storage) to ensure sufficient disk space. Returns task ID for async operation tracking via cloudron_task_status.
Takes no parameters.
Example callreturns →
Check if Cloudron platform updates are available. Returns update information including availability, version, and changelog if an update exists.
Takes no parameters.
Example callreturns →
Apply available Cloudron platform update. DESTRUCTIVE OPERATION - services will restart during update. Performs pre-flight validation to check update is available and recommends backup. Returns task ID for async operation tracking via cloudron_task_status.
Takes no parameters.
Example callreturns →
List all groups on the Cloudron instance. Returns group details including ID, name, and creation date. Groups are sorted alphabetically by name.
Takes no parameters.
Example callreturns →
Create a new group on the Cloudron instance. Groups can be used for access control and user organization.
Takes no parameters.
Example callreturns →
List all platform services (read-only diagnostics). Returns status of Cloudron infrastructure services like databases (MySQL, PostgreSQL, MongoDB), mail, and other platform components. This is diagnostic information - services are managed automatically by Cloudron.
Takes no parameters.
Example callreturns →
Create a backup of a specific application. Performs pre-flight storage check (requires 5GB minimum). Returns task ID for async operation tracking via cloudron_task_status.
Takes no parameters.
Example callreturns →
Restore an application from a backup. DESTRUCTIVE OPERATION - current app data will be replaced. Performs pre-flight validation to check backup exists and storage is sufficient. Returns task ID for async operation tracking via cloudron_task_status.
Takes no parameters.
Example callreturns →
Clone an existing application to a new location. Creates a duplicate of the app with its data and configuration. Performs pre-flight validation to check source app exists and target location is available. Returns task ID for async operation tracking via cloudron_task_status.
Takes no parameters.
Example callreturns →
Repair a broken application. Attempts automatic repair of apps in error state. Use when an app is unhealthy or has installation issues. Returns task ID for async operation tracking via cloudron_task_status.
Takes no parameters.
Example callreturns →
Update an application to a newer version. Performs pre-flight validation to check app exists and is in installed state. Returns task ID for async operation tracking via cloudron_task_status.
Takes no parameters.
Example callreturns →
Fetch real package examples from git.cloudron.io. Finds the repository for a given App Store ID and returns the content of key files (CloudronManifest.json, Dockerfile, start.sh).
Takes no parameters.
Example callreturns →
Get interactive, topic-specific guidance for creating Cloudron packages. Provides documentation, best practices, and reference implementation examples for packaging web applications for Cloudron.
Takes no parameters.
Example callreturns →
Generate a complete Cloudron package scaffold with all required files (CloudronManifest.json, Dockerfile, start.sh, test/test.js). Provides ready-to-use templates customized for your application type, addons, and authentication method.
Takes no parameters.
Example callreturns →
Validate Cloudron package files (CloudronManifest.json, Dockerfile, start.sh) for errors and best practices. Returns detailed validation report with errors, warnings, and suggestions.
Takes no parameters.
Example callreturns →
Freeyour plan
$0 forever
- Every tool, no call limit
- No card, no account needed
- Source published under a licence you can read
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because nothing bills
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable. Cloudron costs nothing to install and nothing to call, 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: $8.42
$16.58 left
ATrust score 96 / 100
Release 0.2.0 · scanned 26 Aug 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 score96
Findings0 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digest0bacbba0389d9fa53c8a339d2b23ab4e4d9300ed2b3a36c2c1a6e53d3f7d11b3
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| 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 (18 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. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| cloudron_list_apps | no tags | |
| cloudron_get_app | no tags | |
| cloudron_get_status | no tags | |
| cloudron_task_status | no tags | |
| cloudron_cancel_task | no tags | |
| cloudron_check_storage | no tags | |
| cloudron_validate_operation | no tags | |
| cloudron_control_app | no tags | |
| cloudron_configure_app | no tags | |
| cloudron_list_backups | no tags | |
| cloudron_create_backup | no tags | |
| cloudron_list_users | no tags | |
| cloudron_search_apps | no tags | |
| cloudron_validate_manifest | no tags | |
| cloudron_create_user | no tags | |
| cloudron_get_logs | sensitive-source | |
| cloudron_uninstall_app | no tags | |
| cloudron_install_app | 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 digest0bacbba0389d9fa5
Scanned2026-08-26
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
Pinned to 0.2.0 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
0.2.0
undated
installedNo release note was published with this version.
—
no reviews yet
Reviews are earned
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Reviews are earned
Writing one takes an account with at least 50 real tool calls against Cloudron in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
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 an account with 50 real tool calls against it.