platform-mcp
A read-only MCP server that turns an AI agent into a GCP platform engineer for investigating incidents, taking inventory, and surfacing cost-optimization opportunities across multiple GCP environments.
List environments to see which GCP projects are configured and which is the default.
Investigate logs and errors by querying Cloud Logging, fetching recent high-severity errors, and listing grouped error reports from Error Reporting.
Explore metrics and alerting by querying Cloud Monitoring time series, listing alert policies, and listing uptime checks.
Surface cost opportunities with billing account info, BigQuery cost breakdowns, and cost recommendations (including auto-discovered locations).
Take resource inventory by searching assets via Cloud Asset Inventory and listing Compute Engine VMs, Cloud Run services, GKE clusters, and Cloud SQL instances.
Target any environment (e.g. staging, production) per call, or fall back to the default environment — all operations are strictly read-only.
Provides read-only tools for investigating incidents, taking inventory, and surfacing cost-optimization opportunities in Google Cloud projects, using APIs for logging, monitoring, error reporting, resource inventory, cost recommendations, and more.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@platform-mcp List all compute instances in us-central1"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
platform-mcp
mcp-name: io.github.deBilla/platform-mcp
A read-only Model Context Protocol server that turns an AI agent (Claude Code, Claude Desktop, or any MCP client) into a GCP platform engineer. Point it at your Google Cloud projects and ask it to investigate incidents, take inventory, and surface cost-optimization opportunities — all without any ability to change your infrastructure.
Observation only. No tool in this server mutates state. Combined with a viewer-only identity (below), that gives you a hard, defense-in-depth guarantee that an agent can look but never touch.
What it can do
Area | Tools |
Environments |
|
Logs & errors |
|
Metrics & alerting |
|
Cost & recommendations |
|
Resource inventory |
|
Typical prompts once it's connected:
"What are the top error groups in the last 24 hours, and which one is newest?"
"Which GKE node pools are over-provisioned? Show mean CPU against machine type."
"Where can I reduce spend in this project?"
Related MCP server: k8s-readonly-mcp
Multiple environments
One server can reach several projects. Define them under
PLATFORM_MCP_ENVIRONMENTS (see Configuration) and the agent
picks one from the wording of your prompt:
"Any errors in staging in the last hour?"
"Compare Cloud Run services between staging and prod."
Every tool takes an optional environment argument. Omit it and the default
environment is used; pass environment="production" to target another. Names,
any aliases you define, common shorthands (prod, stg, qa, …) and bare
project ids all resolve. An unrecognized name is an error listing the valid
options — a typo can never silently retarget the wrong project.
Each environment carries its own service account, so staging and production are
reached through separate identities from the same process, and every result
echoes back the environment and project it came from.
Requirements
Python 3.11+
A Google Cloud project and credentials (your own login, or a service account)
Install
uvx platform-mcp # no install step; uv fetches it on demand
pipx install platform-mcp # or keep it on PATHFrom a checkout, for development:
git clone https://github.com/deBilla/platform-mcp.git
cd platform-mcp
python3 -m venv .venv
./.venv/bin/pip install -e ".[dev]"Check your setup
platform-mcp doctorThis checks, for every configured environment, that Application Default Credentials exist, that the read-only service account can be impersonated, that a real API read succeeds, and that the billing export is readable — printing the exact command to fix whatever fails. Run it before reporting a problem.
One-time GCP setup
Run these once per project you want to reach — staging and production each need their own APIs enabled and their own read-only service account.
1. Enable the APIs the tools depend on:
gcloud services enable \
logging.googleapis.com monitoring.googleapis.com clouderrorreporting.googleapis.com \
recommender.googleapis.com cloudasset.googleapis.com cloudbilling.googleapis.com \
bigquery.googleapis.com \
--project YOUR_PROJECT_ID2. Grant read-only access to the identity the server runs as.
For local development with your own login (Application Default Credentials):
gcloud auth application-default loginThe identity needs these viewer roles on the project, plus roles/billing.viewer
on the billing account:
roles/viewer # broad read (compute, run, gke, sql via Asset Inventory)
roles/logging.viewer
roles/monitoring.viewer
roles/errorreporting.viewer
roles/recommender.viewer
roles/cloudasset.viewer
roles/bigquery.dataViewer # only for get_cost_breakdown
roles/bigquery.jobUser # only for get_cost_breakdown3. (Recommended) Use a dedicated read-only service account instead of your
login. platform-mcp setup does every step below, is safe to re-run, and prints
the config stanza at the end. It ships with the package, so there is nothing to
clone:
uvx platform-mcp setup \
--project YOUR_PROJECT_ID \
--user you@example.com \
--billing-dataset YOUR_BILLING_PROJECT:billing # optionalOr by hand:
PROJECT=YOUR_PROJECT_ID
gcloud iam service-accounts create platform-mcp-ro \
--display-name "platform-mcp read-only" --project $PROJECT
SA=platform-mcp-ro@$PROJECT.iam.gserviceaccount.com
for ROLE in roles/viewer roles/logging.viewer roles/monitoring.viewer \
roles/errorreporting.viewer roles/recommender.viewer roles/cloudasset.viewer \
roles/bigquery.jobUser; do
gcloud projects add-iam-policy-binding $PROJECT \
--member="serviceAccount:$SA" --role="$ROLE" --condition=None
done
# Let your own login impersonate it (no key file to manage):
gcloud iam service-accounts add-iam-policy-binding $SA \
--member="user:you@example.com" \
--role="roles/iam.serviceAccountTokenCreator" --project $PROJECTThe grant everyone forgets. roles/bigquery.jobUser above only lets the
account start a query; it grants no access to any data. A billing export
almost always lives in a different project, so the account also needs read
on that dataset. Without it get_cost_breakdown returns 403 while every other
tool works, which reads like a bug in the tool rather than a missing grant:
bq add-iam-policy-binding \
--member="serviceAccount:$SA" --role=roles/bigquery.dataViewer \
YOUR_BILLING_PROJECT:billingIf you lack admin on the billing project, that one line is what to send to
someone who has it. platform-mcp doctor checks it and says which side is
missing.
Then reference it as that environment's impersonate value in
PLATFORM_MCP_ENVIRONMENTS (preferred — no key file), or point at a downloaded
key via GOOGLE_APPLICATION_CREDENTIALS.
Impersonation is performed by whatever identity your ADC resolves to. If your ADC is itself an impersonated service account, that SA — not your user — needs
roles/iam.serviceAccountTokenCreatoron eachplatform-mcp-ro.
Security model
Read-only is enforced by IAM, not by OAuth scope. The server requests the
broad cloud-platform scope and stays read-only purely because it never calls a
mutating API. Do not rely on the code alone — run it under a viewer-only
identity (step 3 above) so the credential itself is incapable of writing,
regardless of what code executes. This gives you two independent layers: the
server doesn't try to write, and the identity couldn't if it did.
With multiple environments this stays per-project: each environment authenticates as its own service account, so a staging identity is never used to reach production. Grant each one viewer-only access to its project alone.
Configuration
The friendliest option is a config file, which keeps project ids and service account emails out of every client config you own:
mkdir -p ~/.config/platform-mcp
cp config.toml.example ~/.config/platform-mcp/config.toml
$EDITOR ~/.config/platform-mcp/config.tomlWith that in place, registering the server takes no environment variables at
all. Point PLATFORM_MCP_CONFIG elsewhere to use a different file — a copy
committed to your infrastructure repo, for instance.
Environment variables still work and always win over the file, so an existing setup keeps running unchanged and a one-off override needs no edit:
Variable | Purpose |
| JSON map of environment name → settings. The recommended way to configure the server. |
| Environment used when a tool call omits |
| Path to a read-only SA key file (alternative to impersonation). |
PLATFORM_MCP_ENVIRONMENTS holds a JSON object; each entry accepts:
Key | Purpose |
| Required. GCP project id. |
| Read-only SA to impersonate for this environment (no key file needed). |
| Fully-qualified BigQuery billing export table, required only for |
| Extra names the agent may use for this environment. |
A bare string value is shorthand for {"project": "..."}. As JSON inside
.mcp.json the quotes must be escaped; unescaped it reads:
{
"staging": {
"project": "my-app-staging",
"impersonate": "platform-mcp-ro@my-app-staging.iam.gserviceaccount.com"
},
"production": {
"project": "my-app",
"impersonate": "platform-mcp-ro@my-app.iam.gserviceaccount.com",
"billing_export_table": "my-app.billing.gcp_billing_export_v1_XXXXXX"
}
}Single-environment mode. If PLATFORM_MCP_ENVIRONMENTS is unset the server
behaves as before, exposing one environment named default:
Variable | Purpose |
| Target project. Falls back to your ADC default project if unset. |
| Read-only SA to impersonate. Also the fallback for registry entries with no |
| Billing export table. Also the fallback for registry entries with no |
Register with a client
Claude Code — with a config file in place, this is the whole thing:
claude mcp add platform-mcp --scope user -- uvx platform-mcpClaude Desktop — needs an absolute path to uvx; see
Claude Desktop for the full walkthrough.
Without a config file, add the environment variables from
.mcp.json.example to either form.
Skip the approval prompt
Every tool here is read-only, so approving each call individually adds nothing. Allow the whole server once, in Claude Code settings:
{ "permissions": { "allow": ["mcp__platform-mcp__*"] } }The glob must sit after a literal mcp__<server>__ prefix — an unanchored
pattern like mcp__* is ignored with a warning and approves nothing.
MCP Inspector — for interactive testing:
uvx --with 'mcp[cli]' mcp dev src/platform_mcp/server.pyClaude Desktop
Installing for a teammate who uses Claude Desktop rather than the CLI. It works the same as Claude Code, with one failure mode the CLI does not have.
Claude Desktop does not inherit your shell PATH. It launches from the
Finder, so uvx and anything installed by Homebrew or uv are invisible to it.
A config that says "command": "uvx" fails with ENOENT — the server never
starts, and the error names the command rather than the reason. The command
path must be absolute.
What does not break is credentials. Application Default Credentials are a
file the Google libraries read directly, so gcloud is needed once, in a
terminal, to create that file — not at runtime. The config file is found the
same way, from the home directory, whatever launched the server.
Before you start: the admin grant
Each person impersonates the read-only service accounts, so an admin runs this
once per person, per environment (the platform-mcp setup script does it for
whoever runs it, but not for anyone else):
gcloud iam service-accounts add-iam-policy-binding \
platform-mcp-ro@YOUR_PROJECT_ID.iam.gserviceaccount.com \
--member="user:teammate@example.com" \
--role="roles/iam.serviceAccountTokenCreator" --project YOUR_PROJECT_IDWithout it everything installs fine and doctor fails at the impersonation
step.
1. Install uv (macOS)
An analyst's laptop usually has neither Homebrew nor the Xcode Command Line
Tools, and nothing here needs them. Avoid git, make and the stock
/usr/bin/python3 along the way — they are stubs that pop a dialog offering to
install a gigabyte of developer tooling. uv is a standalone binary:
curl -LsSf https://astral.sh/uv/install.sh | sh
which uvx # note this absolute path — Claude Desktop needs itTypically /Users/<you>/.local/bin/uvx.
2. Install the Google Cloud CLI
The tarball bundles its own Python, so it needs nothing else. Avoid
brew install --cask google-cloud-sdk: Homebrew itself requires the Command
Line Tools. Pick the build for your chip — uname -m prints arm64 for Apple
Silicon, x86_64 for Intel:
# Apple Silicon
curl -O https://dl.google.com/dl/cloudsdk/channels/rapid/downloads/google-cloud-cli-darwin-arm.tar.gz
tar -xzf google-cloud-cli-darwin-arm.tar.gz
# Intel — same, with the other file
# curl -O https://dl.google.com/dl/cloudsdk/channels/rapid/downloads/google-cloud-cli-darwin-x86_64.tar.gz
# tar -xzf google-cloud-cli-darwin-x86_64.tar.gz
./google-cloud-sdk/install.sh --quiet3. Authenticate
./google-cloud-sdk/bin/gcloud auth application-default loginLog in as yourself. If your ADC is itself an impersonated service account, that account — not you — becomes the identity doing the impersonation, and it will not hold the grant above.
4. Write the config file
mkdir -p ~/.config/platform-mcp
touch ~/.config/platform-mcp/config.toml
open -e ~/.config/platform-mcp/config.toml # or any editordefault_environment = "staging"
[environments.staging]
project = "my-app-staging"
impersonate = "platform-mcp-ro@my-app-staging.iam.gserviceaccount.com"
[environments.production]
project = "my-app"
impersonate = "platform-mcp-ro@my-app.iam.gserviceaccount.com"
billing_export_table = "my-app.billing.gcp_billing_export_v1_XXXXXX"See Configuration for every key.
5. Check it worked
~/.local/bin/uvx platform-mcp doctorEvery environment should pass. Fix anything that fails before touching Claude Desktop — a server that cannot authenticate still starts, and then every tool call errors.
6. Edit the Claude Desktop config
Settings → Developer → Edit Config opens it, or edit it directly:
OS | File |
macOS |
|
Windows |
|
(Settings → Connectors lists hosted connectors; a local server like this one is not added there.)
The file usually already exists and holds your Desktop preferences. Add
mcpServers as one more top-level key — do not replace the file, or you will
lose those settings:
{
"preferences": { "...": "your existing settings, left alone" },
"mcpServers": {
"platform-mcp": {
"command": "/Users/YOU/.local/bin/uvx",
"args": ["platform-mcp@latest"]
}
}
}Replace /Users/YOU/.local/bin/uvx with what which uvx printed. On Windows
the path looks like C:\\Users\\YOU\\.local\\bin\\uvx.exe — backslashes doubled
in JSON. @latest makes each launch pick up new releases.
Check it still parses before restarting — a stray comma disables every server, silently. This uses only what ships with macOS:
osascript -l JavaScript -e 'function run(a){ObjC.import("Foundation");JSON.parse($.NSString.stringWithContentsOfFileEncodingError(a[0],4,null).js);return "valid"}' \
~/Library/Application\ Support/Claude/claude_desktop_config.json7. Restart Claude Desktop
Quit it fully (Cmd-Q, not just closing the window) and reopen. Then ask
"list the configured environments" — it should answer from list_environments.
If it does not appear, the logs are in ~/Library/Logs/Claude/
(mcp-server-platform-mcp.log). ENOENT there means the command path is
wrong.
Why not a key file?
You can skip steps 2–3 by pointing GOOGLE_APPLICATION_CREDENTIALS (in the
server's env block) at a downloaded service-account key. Think twice: a key
is a long-lived credential sitting on a laptop, and the production read-only
account can read every log, metric and billing row in that project.
application-default login issues short-lived tokens tied to a person, and
removing one grant revokes that person alone.
Observability
Every tool call appends one JSON line to ~/.local/state/platform-mcp/audit.jsonl:
{"ts":"2026-08-30T18:20:11+0800","tool":"query_logs","environment":"production",
"project":"my-app","duration_ms":412,"count":50,"bytes":18422,"error":null}Free-text arguments are recorded by name only — a Cloud Logging filter can carry
user ids from the logs being searched, and the audit file must not become a
second copy of that. Set PLATFORM_MCP_AUDIT_LOG to another path, or to off.
Diagnostic logs go to stderr (PLATFORM_MCP_LOG_LEVEL to adjust); in stdio
transport stdout carries the protocol, so nothing else may be written there. In
Claude Code, read them with claude --debug=mcp.
For a record that does not depend on this server at all, enable Data Access audit logs in GCP for the read-only service accounts. Token minting already appears in Admin Activity logs without any configuration.
Development
./.venv/bin/python -m pytestThe suite runs against an in-memory MCP client — no network and no GCP
credentials — and covers environment resolution, the tool contract,
annotations, error translation and the audit log. The only subprocess is
bash -n over the packaged setup script, which is skipped where bash is absent.
The setup script lives at src/platform_mcp/scripts/ because it ships as
package data; platform-mcp setup runs it from wherever the package is
installed, so the quickstart needs no checkout.
Notes
All tools cap result counts and truncate long payloads to stay token-friendly.
GCP clients are built lazily and cached per environment, so switching between staging and production mid-conversation costs one client construction each.
Cost recommenders are zonal/regional;
list_cost_recommendationsauto-discovers the locations where you have resources (via Asset Inventory) and fans out, skipping locations and recommenders that are empty or unavailable. It reportsskipped_callsand fails loudly if it cannot discover any location, because "I could not look" and "there is nothing to save" must not look alike.get_cost_breakdownuses parameterized BigQuery queries with a whitelisted set of group-by columns, and filters to the selected environment's project. A billing export covers the whole billing account, so passall_projects=truewhen you want account-wide totals.
License
MIT © 2026 Dimuthu Wickramanayake
Available Tools
16 toolsget_billing_infoARead-onlyIdempotent
Return 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.
Inputs: environment.
get_cost_breakdownARead-onlyIdempotent
Summarize 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.
Inputs: days, limit, group_by, environment, +1 more.
get_recent_errorsARead-onlyIdempotent
Return 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.
Inputs: hours, limit, service, environment.
list_alert_policiesARead-onlyIdempotent
List 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.
Inputs: limit, environment.
list_cloud_run_servicesARead-onlyIdempotent
List Cloud Run services.
Args: limit: Maximum number of services to return. environment: Which configured GCP environment to query, e.g. 'staging' or 'production'. Omit to use the default environment.
Inputs: limit, environment.
list_compute_instancesARead-onlyIdempotent
List Compute Engine VM instances with location and status.
Args: limit: Maximum number of instances to return. environment: Which configured GCP environment to query, e.g. 'staging' or 'production'. Omit to use the default environment.
Inputs: limit, environment.
list_cost_recommendationsARead-onlyIdempotent
Aggregate 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.
Inputs: locations, environment, limit_per_call.
list_environmentsARead-onlyIdempotent
List 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.
Inputs: no named parameters.
list_error_groupsARead-onlyIdempotent
List 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.
Inputs: hours, limit, service, environment.
list_gke_clustersARead-onlyIdempotent
List GKE (Kubernetes Engine) clusters.
Args: limit: Maximum number of clusters to return. environment: Which configured GCP environment to query, e.g. 'staging' or 'production'. Omit to use the default environment.
Inputs: limit, environment.
list_recommendationsARead-onlyIdempotent
List 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.
Inputs: recommender_id (required), limit, location, environment.
list_sql_instancesARead-onlyIdempotent
List Cloud SQL instances.
Args: limit: Maximum number of instances to return. environment: Which configured GCP environment to query, e.g. 'staging' or 'production'. Omit to use the default environment.
Inputs: limit, environment.
list_uptime_checksARead-onlyIdempotent
List 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.
Inputs: limit, environment.
query_logsARead-onlyIdempotent
Query 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.
Inputs: limit, filter, freshness, environment.
query_metricARead-onlyIdempotent
Query 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.
Inputs: metric_type (required), limit, window, aligner, +3 more.
search_assetsARead-onlyIdempotent
Search 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.
Inputs: limit, query, asset_types, environment, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 16 tools
Most tools target clearly distinct GCP resources or actions, but query_logs and get_recent_errors overlap as general vs. error-filtered log queries, and list_cost_recommendations vs. list_recommendations could cause some selection uncertainty despite their aggregate/specific distinction.
All tools follow a consistent verb_noun pattern: list_* for enumeration, query_* for log/metric queries, get_* for specific lookups, and search_assets for asset discovery. There are no mixed naming conventions or unpredictable verbs.
At 16 tools, the server is slightly above the ideal 3-15 range, but the count is justified by the broad GCP read-only scope covering logs, errors, metrics, alerts, costs, billing, and multiple resource types. No tool feels redundant enough to remove.
The toolset covers core platform observability, cost, billing, and resource discovery well, with no obvious dead ends for typical read-only queries. Minor gaps exist such as lacking detailed single-resource fetches and specific listings for services like Cloud Storage or BigQuery, though search_assets partially mitigates these.
Maintenance
Related MCP Connectors
The Google Compute Engine MCP server is a fully-managed Model Context Protocol server that provides tools to manage Google Compute Engine resources through AI agents. It enables capabilities including instance management (creating, starting, stopping, resetting, listing), disk management, handling instance templates and group managers, viewing machine and accelerator types, managing images, and accessing reservation and commitment information. The server operates as a zero-deployment, enterprise-grade endpoint at https://compute.googleapis.com/mcp with built-in IAM-based security.
The Google GKE MCP server is a managed Model Context Protocol server that provides AI applications with tools to manage Google Kubernetes Engine (GKE) clusters and Kubernetes resources. It exposes a structured, discoverable interface that allows AI agents to interact with GKE and Kubernetes APIs, enabling them to inspect cluster configurations, retrieve Kubernetes resource YAMLs, monitor operations like cluster upgrades, diagnose issues, and optimize costs—all without needing to parse text output or use complex kubectl commands.
Read-only MCP server for AIStatusDashboard status, incidents, metrics, and fallback recommendations.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA read-only MCP server for AI coding agents to inspect repositories, audit code quality, route engineering skills, and plan safe issue/PR workflows.1MIT
- AlicenseAqualityDmaintenanceA read-only MCP server for inspecting Kubernetes clusters, allowing LLMs to list resources, describe pods, and read logs without mutation.5MIT
- AlicenseNot gradedqualityDmaintenanceA read-only MCP server that lets an LLM inspect an AWS account — list EC2 instances, S3 buckets, IAM users, and cost — with a structural guarantee against any mutations.MIT
- AlicenseAqualityDmaintenanceA secure, read-only MCP server for AI-powered system monitoring. It provides real-time OS metrics, config discovery, and safe log tailing to enable autonomous infrastructure audits without shell access risks.42ISC