Back to Browse

Mcp MCP Server

Developer ToolsLow Risk9.0MCP RegistryRemote
Free

Server data from the Official MCP Registry

Plug apps, sites and HTML pages into CloudGrid and get a live URL, with databases and AI built in.

About

Plug apps, sites and HTML pages into CloudGrid and get a live URL, with databases and AI built in.

Remote endpoints: streamable-http: https://mcp.cloudgrid.io/mcp

Security Report

9.0
Low Risk9.0Low Risk

Valid MCP server (3 strong, 3 medium validity signals). 1 known CVE in dependencies (0 critical, 1 high severity) Imported from the Official MCP Registry.

Endpoint verified · Requires authentication · 2 issues found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Found in Source Code

Found by scanning the linked source code. This listing connects to a hosted endpoint, so none of this runs on your machine: it describes what the server software does where it is hosted.

env_vars

Applies to the server that hosts this plugin, not to your machine.

database

Applies to the server that hosts this plugin, not to your machine.

file_system

Applies to the server that hosts this plugin, not to your machine.

Shell Command Execution

Runs commands on the server that hosts it, not on your machine.

HTTP Network Access

Connects to external APIs or services over the internet.

How to Connect

Remote Plugin

No local installation needed. Your AI client connects to the remote endpoint directly.

Add this to your MCP configuration to connect:

{
  "mcpServers": {
    "io-github-cloudgrid-io-mcp": {
      "url": "https://mcp.cloudgrid.io/mcp"
    }
  }
}

Documentation

View on GitHub

From the project's GitHub README.

@cloudgrid-io/mcp

An MCP server for CloudGrid. It exposes the CloudGrid actions as MCP tools.

Hosted server

Add this URL to your AI tool as a remote MCP server (in claude.ai and ChatGPT, add it as a custom connector):

https://mcp.cloudgrid.io/mcp

Sign in to CloudGrid when your AI tool asks; the connection uses OAuth. There is nothing to install and nothing to configure. The hosted server carries the tools that call the CloudGrid API directly. How it works and how it is hosted: REMOTE.md.

Local server

The local edition runs on your machine over stdio and adds the tools that wrap the grid CLI (logs, rollbacks, env vars, secrets, scaffolding). Use it in Claude Code, Cursor or Claude Desktop when you build runtime apps from a folder on disk.

Install and sign in to the CLI:

npm install -g @cloudgrid-io/cli
grid login

Then point your MCP client at:

npx -y @cloudgrid-io/mcp

The server reads no credentials of its own. It uses the CLI's stored sign-in at ~/.cloudgrid/credentials; grid_login writes the same file.

One CloudGrid server per client

Add either the hosted server or the local server to a given client, not both. With both, each grid_* tool appears twice and the two hold separate sign-in state, so they can disagree about whether you are signed in. To check, look for duplicate grid_* entries in the client's tool list, or two CloudGrid servers in its MCP or connector settings. Keep the local server where you build runtime apps from folders, and the hosted server in chat-only clients.

Settings (local server)

All optional:

  • CLOUDGRID_TELEMETRY=off: turns off grid_report error reports.
  • HTTPS_PROXY, HTTP_PROXY, NO_PROXY: route API calls through a proxy.
  • NODE_EXTRA_CA_CERTS=/path/to/root-ca.pem: trust an extra root certificate, for networks that inspect TLS.

GRID_AUTH_STALE is out of scope: grids whose owner enforces SSO can return it when your session predates an SSO policy change. The server does not retry; sign in again through Console SSO.

Tools

38 tools registered (15 shared across both editions, 23 local-only). No deprecated aliases. MIN_CLI_VERSION: 0.15.26.

Direct-API tools (both editions)

ToolWrapsSummary
grid_pickupAPIPick up an app: copies any app the user can see into one of their grids as a NEW, separate entity (a fork, like a git...
grid_pullAPIPull an app to continue or edit it IN PLACE, like git clone of the SAME entity: the next plug with its target_entit...
grid_collabAPICollab: grants the signed-in user PUSH ACCESS to the SAME live entity that someone else owns, as a collaborator on th...
grid_create_gridAPICreate a new grid (the workspace the user's apps live in) for the signed-in user, who becomes its admin.
grid_noteAPIRecord a one-paragraph summary of what was built this session and why, for the local edition's optional QA session lo...
grid_plugAPIPlug an app, website, game, or HTML page into CloudGrid at a live public URL.
grid_get_app_sourceAPIRetrieve the CURRENT deployed HTML of an inspiration/drop inline as text, for editing and re-plugging the SAME URL wh...
grid_visibilityAPIChange who can see a CloudGrid inspiration OR runtime app/agent.
grid_check_deployAPICheck whether an async runtime-app build (a deploy, which here means a plug) has finished and the app is live.
grid_list_gridsAPIList the signed-in user's grids, each with slug, name, role, whether it is the active grid, and setup status (render_...
grid_startAPIA short orientation for building with CloudGrid: the account this session is signed in as and its active grid, how to...
grid_get_templatecorpusLoad a specific CloudGrid workflow, template, example, rule, troubleshooting note, or reference doc by kind and name:...
grid_reportAPIReport a genuine CloudGrid failure (a build, deploy, or platform call that failed unexpectedly) to the CloudGrid team...
grid_helloAPICreate a minimal hello page and plug it into the user's grid, returning the live URL.
grid_deletegrid delete entityArchive a CloudGrid inspiration.

The direct-API tools call the platform without the CLI, so they also work in the web edition. grid_login writes the same ~/.cloudgrid/credentials the CLI uses, so the two share one identity.

CLI-wrapping tools (local edition only)

ToolWrapsSummary
grid_loginAPIStart a CLI-free CloudGrid sign-in.
grid_login_statusAPIFinish a browser sign-in started from this server.
grid_create_projectgrid newScaffold a new CloudGrid app or agent folder (cloudgrid.yaml + a web service), optionally pre-declaring resources.
grid_view_logsgrid logsTail recent logs for an entity.
grid_sharegrid visibility setSet an entity's visibility and print its URL.
grid_feedbackgrid feedback listList recent feedback events for the active grid.
grid_whoamigrid whoamiShow the signed-in user and active grid.
grid_switch_gridgrid useSwitch the active grid.
grid_logoutgrid logoutSign out and clear local credentials.
grid_statusgrid statusGrid dashboard, entity detail, or deploy snapshot.
grid_infogrid infoShow metadata for a CloudGrid entity.
grid_get`grid get <gridsentities
grid_describe_gridgrid describe grid <slug> --jsonShow a grid's detail: role, members, spaces, tier, wildcard-TLS state.
grid_edit_existing_appgrid pullContinue/edit an EXISTING entity locally: downloads its source + cloudgrid.yaml and links the folder so the next `gri...
grid_renamegrid renameRename a CloudGrid entity's display name (slug stays the same).
grid_take_offlinegrid unplugTake an entity off the grid.
grid_rollback_deploygrid rollbackRollback an entity to a previous version.
grid_list_versionsgrid versionsList published versions for an entity.
grid_set_envgrid envManage environment variables for an entity.
grid_set_secretgrid secretsSet or list secret names for an entity.
grid_scaffoldgrid scaffoldScaffold service folders declared in cloudgrid.yaml (idempotent).
grid_diagnosegrid doctorRun CloudGrid diagnostics on the local environment.
grid_get_urlgrid open --printReturn the public URL for an entity.

grid_share and grid_visibility overlap on purpose: grid_share wraps the CLI and defaults to link; grid_visibility is direct API, takes an explicit scope, and defaults its target to the session's last drop — it is the one the web edition gets.

All tools carry MCP annotations (readOnlyHint, destructiveHint, openWorldHint) for clients that support them.

Privacy Policy

Full policy: https://cloudgrid.io/privacy

What this MCP server does with your data

Authentication. grid_login opens a browser-based Google sign-in flow via CloudGrid's API (/auth/login). The returned JWT is stored at ~/.cloudgrid/credentials with 0600 permissions — the CLI and the MCP share one credential file by design (auth.js:7-8). The web edition has no sign-in tool: the AI tool's connector signs in with OAuth, and this server issues its own short-lived access token, with the CloudGrid session sealed inside it, so the session is never handed to the AI tool.

Deploying. grid_plug uploads your app files (HTML, source, assets) to https://api.cloudgrid.io/api/v2/plug. Before upload, inline sources are scanned for known API-key patterns (OpenRouter, Anthropic, OpenAI, Google, GitHub, AWS, Slack, Stripe); a match blocks the deploy. This is not a guarantee — a determined model can obfuscate a key past the scan — but it stops the good-faith "embed it so it works" path. Auth headers (Bearer JWT, grid slug) are attached to identify the caller.

Error reporting. grid_report sends an error report to https://api.cloudgrid.io/api/v2/errors. The tool description instructs the model to call it only with the user's explicit consent, and setting CLOUDGRID_TELEMETRY=off disables it unconditionally — but there is no programmatic consent check in the report handler itself. The payload includes an error summary, diagnostic metadata (platform, Node version, transport), a flag recording whether the user agreed to share the conversation (deploy.js:544), and a context object the model supplies — which by its declared shape (register.js:964-975) can carry the failing inputs (for example the HTML or args) and the original request. The transcript itself is not sent by this tool. The report scrub is two-layer: values AND the message field are scanned for known secret shapes (API key prefixes such as sk-ant-, sk-proj-, AKIA…; JWTs; PEM private-key blocks; Bearer tokens; basic-auth URL credentials) and matches are replaced with [REDACTED]. Arbitrary or unknown-shape secrets that do not match a known pattern still transit unredacted. The client-side scrub (scrubReportContext + scrubSecretValues in deploy.js) runs before the POST; the server endpoint applies a server-side key-name filter on top. To keep a secret out of a report, do not place it in the message or context you send, or set CLOUDGRID_TELEMETRY=off to disable reporting entirely.

Version check. At startup the local edition makes one request to https://registry.npmjs.org/@cloudgrid-io/mcp/latest to detect a stale .mcpb install, which never auto-updates. It sends no account data and no user content. The hosted edition does not do this.

QA session log. Off by default. The local (stdio) server posts a per-session QA log to the CloudGrid team only on a machine where a maintainer has turned it on (see CONTRIBUTING.md); a user never sets it. When on, it posts on deploy, error, idle timeout, or process shutdown. The log includes: session metadata (user ID, email, grid slug, client name), the user's first message (scrubbed, capped at 2 000 chars), a per-tool-call trail with allowlisted arg keys only, and an optional narrative set via grid_note or grid_plug's session_note (capped at 4 000 chars). The first message is captured from the CLOUDGRID_USER_REQUEST environment variable (forwarded by Claude Code) or grid_plug's user_request argument (local edition only). The hosted edition sends nothing on its own: its grid_plug has no user_request or session_note, and there is no post on a plug, on idle, or on close. The one hosted post is grid_note, which the user asks for: it POSTs the note to the CloudGrid API (/api/v2/feedback) under the user's own sign-in, with the grid slug and the client name — no email address, no tool-call trail, nothing else from the conversation; signed out, it returns needs_auth and sends nothing. grid_report (both editions) sends a failure report to the CloudGrid API only after the user agrees: the message and context the model passes plus the client name and platform, and the conversation only when they explicitly agree to that. Free-text values (the first message, the narrative, tool arguments, and error messages) pass through a scrubber that redacts JWTs, PEM keys, Bearer tokens, and known provider API-key formats. Identity fields (_keyResult values and the header block) and structured result data bypass the text scrubber.

No other data collection by this server. The server does not track usage analytics or transmit data beyond the flows listed above and the authenticated CloudGrid API calls the individual tools make (e.g. /grids, /pickup, /deploys, /inspirations/{id}/source). CLI-wrapping tools shell out to the CloudGrid grid CLI, which shares the same ~/.cloudgrid/credentials file and does not send additional telemetry through this server. They prefer the CLI bundled in the .mcpb or a compatible grid already on your PATH; if neither is present or new enough, they fall back to npx -y @cloudgrid-io/cli@latest (cli.js:411-424), which downloads and runs the CLI from the npm registry (registry.npmjs.org) on first use — software installation, and the second flow that can reach npm (the startup version check above is the first). Platform-level data handling is covered by the linked privacy policy.

Reviews

No reviews yet

Be the first to review this server!