GCP Platform Engineer vs Anythink Cli
A side-by-side look at the GCP Platform Engineer and Anythink Cli MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose GCP Platform Engineer for cloud platforms work as a local process; choose Anythink Cli for cloud platforms as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose GCP Platform Engineer when
- You need dedicated capabilities in the Cloud Platforms domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
PLATFORM_MCP_CONFIG, PLATFORM_MCP_ENVIRONMENTS, PLATFORM_MCP_DEFAULT_ENVIRONMENT, GOOGLE_APPLICATION_CREDENTIALS. - You want tools like
list_environments, query_logs, get_recent_errors.
Choose Anythink Cli when
- You need dedicated capabilities in the Cloud Platforms domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: other.
- You want tools like
config_use, projects_delete, login_direct.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Cloud Platforms | Cloud Platforms |
| Quality signal | 59/100 · Good | 67/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | other |
| Pricing | Not declared | Freemium |
| Required env vars | PLATFORM_MCP_CONFIGPLATFORM_MCP_ENVIRONMENTSPLATFORM_MCP_DEFAULT_ENVIRONMENTGOOGLE_APPLICATION_CREDENTIALS | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 2 | 6 |
| Directory activity | 2 views 0 installs 0 upvotes | 5 views 0 installs 0 upvotes |
| Tools | 16 | 16 |
| Full listing | View GCP Platform Engineer | View Anythink Cli |
Tools & capabilities
GCP Platform Engineer tools 16
list_environmentsList the GCP environments this server can query and which is the default. Pass one of the returned names as the `environment` argument of any other tool to target that project (e.g. environment='production'). Omitting the argument uses the default environment shown here. Common shorthands such as 'prod' and 'stg' are accepted, as is a bare project id.query_logsQuery Cloud Logging with an advanced-filter expression. Args: filter: Cloud Logging advanced filter (e.g. 'severity>=WARNING AND resource.type="cloud_run_revision"'). Leave empty to match all logs. freshness: How far back to look, e.g. '30m', '1h', '2d'. Default '1h'. limit: Maximum number of entries to return (newest first). environment: Which configured GCP environment to query, e.g. 'staging' or 'production'. Omit to use the default environment. Call list_environments to see what is configured.get_recent_errorsReturn recent log entries at severity ERROR or higher. Args: service: Optional service name to narrow to (matched against resource.labels.service_name and logName). hours: How many hours back to search. Default 1. limit: Maximum number of entries to return (newest first). environment: Which configured GCP environment to query, e.g. 'staging' or 'production'. Omit to use the default environment.list_error_groupsList grouped application errors from Error Reporting with counts. Args: hours: Lookback window; snapped to the nearest supported period (1h, 6h, 1d, 1w, 30d). Default 24. service: Optional service name filter (Error Reporting "service" label). limit: Maximum number of error groups to return (most frequent first). environment: Which configured GCP environment to query, e.g. 'staging' or 'production'. Omit to use the default environment.query_metricQuery a Cloud Monitoring metric time series. Args: metric_type: Metric type, e.g. 'compute.googleapis.com/instance/cpu/utilization'. resource_filter: Optional extra filter, e.g. 'resource.labels.instance_id="123"'. window: How far back to query, e.g. '1h', '6h', '1d'. Default '1h'. aligner: Aggregation across the alignment period: MEAN, MAX, MIN, SUM, COUNT, RATE, PERCENTILE_99. Default MEAN. alignment_period: Bucket size for aggregation, e.g. '1m', '5m'. Default '5m'. limit: Maximum number of time series to return. environment: Which configured GCP environment to query, e.g. 'staging' or 'production'. Omit to use the default environment.list_alert_policiesList Cloud Monitoring alert policies and whether they are enabled. Args: limit: Maximum number of policies to return. environment: Which configured GCP environment to query, e.g. 'staging' or 'production'. Omit to use the default environment.list_uptime_checksList Cloud Monitoring uptime check configurations. Args: limit: Maximum number of uptime checks to return. environment: Which configured GCP environment to query, e.g. 'staging' or 'production'. Omit to use the default environment.list_cost_recommendationsAggregate GCP cost-optimization recommendations (idle/rightsizing/etc). Fans out the cost recommenders across the locations where the project has resources. Recommenders/locations that are empty or not enabled are skipped. Args: locations: Optional comma-separated zones/regions to scan (e.g. 'us-central1,us-central1-a'). If empty, auto-discovers from Asset Inventory (requires the Cloud Asset API). limit_per_call: Max recommendations to pull per recommender+location. environment: Which configured GCP environment to query, e.g. 'staging' or 'production'. Omit to use the default environment.list_recommendationsList recommendations from a specific recommender at a specific location. Args: recommender_id: Recommender id, e.g. 'google.compute.instance.MachineTypeRecommender' or 'google.iam.policy.Recommender'. location: Zone (e.g. 'us-central1-a'), region (e.g. 'us-central1'), or 'global' depending on the recommender. Default 'global'. limit: Maximum number of recommendations to return. environment: Which configured GCP environment to query, e.g. 'staging' or 'production'. Omit to use the default environment.get_cost_breakdownSummarize recent spend from the BigQuery billing export. By default this reports spend for the selected environment's project only. A billing export table covers every project on the billing account, and several environments commonly share one table, so an unfiltered query would return identical account-wide totals for staging and production. Only the environment holding the export needs 'billing_export_table' set: one billing account exports to one project, and that export already covers every project on the account. Asking any other environment for costs returns an error naming the one that has it. Args: group_by: One of 'service', 'sku', 'project', 'region'. Default 'service'. days: Lookback window in days over usage_start_time. Default 30. limit: Max rows returned (highest net cost first). all_projects: Report the whole billing account instead of just this environment's project. Pair with group_by='project' to compare projects; the totals then are not specific to this environment. environment: Which configured GCP environment to bill against, e.g. 'staging' or 'production'. Omit to use the default environment.get_billing_infoReturn the billing account linked to the project and its status. Args: environment: Which configured GCP environment to inspect, e.g. 'staging' or 'production'. Omit to use the default environment.search_assetsSearch all cloud resources in the project via Cloud Asset Inventory. Args: asset_types: Optional comma-separated asset types to filter, e.g. 'compute.googleapis.com/Instance,run.googleapis.com/Service'. query: Optional free-text/structured query, e.g. 'state:RUNNING' or 'location:us-central1'. limit: Maximum number of resources to return. Default 50; raise it when you know you need a full inventory, since each resource costs context. include_labels: Include resource labels. Off by default because deployment labels are usually the largest part of the response and rarely answer the question being asked. environment: Which configured GCP environment to search, e.g. 'staging' or 'production'. Omit to use the default environment. Call list_environments to see what is configured.- +4 more on the listing page
Anythink Cli tools 16
config_useSwitch the active project profile that the 'cli' tool's commands operate against. Use this to move between already-connected projects without re-authenticating. The profile must already exist (created by 'projects_use' or 'login_direct'); run 'config_show' to see available profile names. Returns confirmation, or an error if the profile does not exist.projects_deletePermanently delete a project and tear down its backend instance, including its database and stored data. This is destructive and irreversible — always confirm with the user first, and prefer matching by a specific id over a short prefix to avoid removing the wrong project. Requires an active billing account (set one with 'accounts_use'). Returns the deleted project's name and id on success.login_directStore credentials directly for a project (bypasses billing login). Use this when you already have an org ID and API key or JWT token.projects_useConnect to a project and save it as the active profile so the 'cli' tool's data, entities, users, and other commands target it. Resolves the project, then either stores the API key you pass or exchanges a transfer token for project-scoped credentials automatically. Requires an active billing account (set one with 'accounts_use'); the project must be Active (see 'projects_list'). Returns the saved profile name, org id, API URL, and auth method.logoutRemove the saved credentials for a project profile from local CLI config. Use this to disconnect from a project or clear a stale token; it deletes only the stored profile locally and does not revoke the token server-side or affect the project. Omit the profile to remove the currently active one. Run 'config_show' to see profile names.signupRegister a brand-new Anythink platform account with email and password. Use this only when the user has no account yet; if they already have one, use 'login' instead. This creates the top-level user identity — it does not create a billing account or project (do that with 'accounts_create' and 'projects_create' after logging in). On success the user may need to click an email confirmation link before 'login' works; tell them to confirm, then call 'login'.accounts_createCreate a new billing account (organization) to hold projects and payment details. Requires a prior platform login (use the 'login' tool first). The new account is automatically set as the active account, so subsequent 'projects_create' / 'projects_list' calls target it without further setup. Returns the new account's id and name. Most users need only one account — call 'accounts_list' first to check whether a suitable one already exists.config_removeDelete a saved project profile from the local CLI configuration. Removes only the locally stored credentials and settings — it does not delete the project or revoke tokens server-side (to remove the project itself, use 'projects_delete'). Run 'config_show' to see profile names. Returns confirmation, or a not-found message.projects_listList the projects (provisioned backend instances) in a billing account. Requires platform login and an active billing account (set one with 'accounts_use'). Returns each project's id, name, description, region, org id, status (Initializing/Provisioning/Active/Suspended/Terminated/Error), API URL, and creation date. Use this to find a project's id before connecting with 'projects_use' or removing it with 'projects_delete'.loginLog in to the Anythink platform with email and password. Returns a session token used for account and project management. For Google sign-in, use the 'login_google' tool.accounts_useSet the active billing account that project commands operate on. Call this after 'login' when you belong to more than one account, before using 'projects_list', 'projects_create', or 'projects_use'. Accepts a full account UUID or a unique prefix; run 'accounts_list' to see valid ids. Returns the resolved account name and id, or an error if no account matches.login_googleSign in to the Anythink platform with Google. Opens the user's browser to Google's consent screen and waits for them to approve, then stores the session token. The browser step must be completed by the user; everything before and after is tool-driven. This does NOT pick a billing account or project — after it returns, call 'accounts_list' then 'accounts_use', and 'projects_list' then 'projects_use'. Needs a local browser, so it only works over stdio (not the hosted HTTP server).- +4 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
GCP Platform Engineer
{
"mcpServers": {
"gcp-platform-engineer": {
"command": "uvx",
"args": [
"platform-mcp"
],
"env": {
"PLATFORM_MCP_CONFIG": "YOUR_PLATFORM_MCP_CONFIG_HERE",
"PLATFORM_MCP_ENVIRONMENTS": "YOUR_PLATFORM_MCP_ENVIRONMENTS_HERE",
"PLATFORM_MCP_DEFAULT_ENVIRONMENT": "YOUR_PLATFORM_MCP_DEFAULT_ENVIRONMENT_HERE",
"GOOGLE_APPLICATION_CREDENTIALS": "YOUR_GOOGLE_APPLICATION_CREDENTIALS_HERE"
}
}
}
}
Anythink Cli
{
"mcpServers": {
"anythink-cloud-anythink-cli": {
"command": "npx",
"args": [
"-y",
"@anythink-cloud/mcp"
]
}
}
}
Frequently asked questions
GCP Platform Engineer is categorized under Cloud Platforms and uses a local stdio subprocess. Anythink Cli belongs to Cloud Platforms and uses a local stdio subprocess. Pick GCP Platform Engineer for cloud platforms work and Anythink Cli for cloud platforms.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
GCP Platform Engineer has no declared pricing — check the project's own site. Anythink Cli is listed as freemium — a free tier with paid plans. Auth: other. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add gcp-platform-engineer and anythink-cloud-anythink-cli as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, GCP Platform Engineer has a quality signal of 59/100 (Good) with 2 views, 0 installs and 2 GitHub stars. Anythink Cli has 67/100 (Great) with 5 views, 0 installs and 6 GitHub stars.