GCP Billing and Monitoring MCP Server
Provides comprehensive tools for managing Google Cloud resources including billing analysis with cost optimization insights, querying and filtering Cloud Logging entries, and retrieving metrics from Cloud Monitoring for infrastructure observability.
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., "@GCP Billing and Monitoring MCP Server analyze costs for my-app-prod-123 over the last 30 days"
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.
GCP Billing and Monitoring MCP Server
A Model Context Protocol server that connects to Google Cloud services to provide context and tools for interacting with your Google Cloud resources.
Services
Supported Google Cloud services:
Billing
Manage and analyse Google Cloud billing with cost optimisation insights:
Tools: gcp-billing-list-accounts, gcp-billing-get-account-details, gcp-billing-list-projects, gcp-billing-get-project-info, gcp-billing-list-services, gcp-billing-list-skus, gcp-billing-analyse-costs, gcp-billing-detect-anomalies, gcp-billing-cost-recommendations, gcp-billing-service-breakdown
Example prompts:
"Show me all my billing accounts"
"Analyse costs for project my-app-prod-123 for the last 30 days"
"Generate cost recommendations for billing account billingAccounts/123456-789ABC-DEF012"
"Check for billing anomalies in project my-ecommerce-456"
Logging
Query and filter log entries from Google Cloud Logging:
Tools: gcp-logging-query-logs, gcp-logging-query-time-range, gcp-logging-search-comprehensive
Example prompts:
"Show me logs from project my-app-prod-123 from the last hour with severity ERROR"
"Search for logs containing 'timeout' from service my-api in project backend-456"
"Query logs for resource type gce_instance in project compute-prod-789"
Monitoring
Retrieve and analyse metrics from Google Cloud Monitoring:
Tools: gcp-monitoring-query-metrics, gcp-monitoring-list-metric-types, gcp-monitoring-query-natural-language
Example prompts:
"Show me CPU utilisation metrics for project web-app-prod-123 for the last 6 hours"
"List available metric types for Compute Engine in project infrastructure-456"
"Query memory usage for instances in project backend-services-789"
Related MCP server: GCP MCP
Quick Start
Once configured, you can interact with Google Cloud services using natural language:
"What are my current billing costs for project my-webapp-prod-123?"
"Find logs containing 'database timeout' from project backend-prod-321 yesterday"
"What's the CPU usage of Compute Engine instances in project infrastructure-987?"Authentication
This server supports two methods of authentication with Google Cloud:
Service Account Key File (Recommended): Set the
GOOGLE_APPLICATION_CREDENTIALSenvironment variable to the path of your service account key file. This is the standard Google Cloud authentication method.Environment Variables: Set
GOOGLE_CLIENT_EMAILandGOOGLE_PRIVATE_KEYenvironment variables directly. This is useful for environments where storing a key file is not practical.
The server will also use the GOOGLE_CLOUD_PROJECT environment variable if set, otherwise it will attempt to determine the project ID from the authentication credentials.
Installation
# Clone the repository
git clone https://github.com/RadiumGu/gcp-billing-and-monitoring-mcp.git
cd gcp-billing-and-monitoring-mcp
# Install dependencies
pnpm install
# Build
pnpm buildAuthenticate to Google Cloud:
gcloud auth application-default loginConfigure the mcpServers in your client:
{
"mcpServers": {
"gcp-billing-and-monitoring-mcp": {
"command": "node",
"args": [
"/path/to/gcp-billing-and-monitoring-mcp/dist/index.js"
],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "/path/to/your/service-account-key.json"
}
}
}
}Development
Starting the server
# Build the project
pnpm build
# Start the server
pnpm startDevelopment mode
# Build the project
pnpm build
# Start the server and inspector
npx -y @modelcontextprotocol/inspector node dist/index.jsTroubleshooting
Server Timeout Issues
If you encounter timeout issues when running the server with Smithery, try the following:
Enable debug logging by setting
debug: truein your configurationEnsure
lazyAuth: trueis set to defer authentication until it's actually neededEnsure your credentials file is accessible and valid
Check the logs for any error messages
Important: Authentication is still required for operation, but with lazy loading enabled, the server will start immediately and authenticate when needed rather than during initialization.
Authentication Issues
The server supports two methods of authentication:
Service Account Key File: Set
GOOGLE_APPLICATION_CREDENTIALSenvironment variable to the path of your service account key fileEnvironment Variables: Set
GOOGLE_CLIENT_EMAILandGOOGLE_PRIVATE_KEYenvironment variables
If you're having authentication issues, make sure:
Your service account has the necessary permissions
The key file is properly formatted and accessible
Environment variables are correctly set
Available Tools
40 toolsgcp-billing-analyse-costsAnalyse Billing CostsC
Perform detailed cost analysis with trends and insights for Google Cloud billing data
Inputs: billingAccountName (required), startDate (required), endDate (required), projectId, +2 more.
gcp-billing-cost-recommendationsGenerate Cost RecommendationsB
Generate cost optimisation recommendations with potential savings for Google Cloud billing
Inputs: billingAccountName (required), projectId, minSavingsAmount, priority.
gcp-billing-detect-anomaliesDetect Cost AnomaliesC
Detect unusual cost patterns and spending anomalies in Google Cloud billing data
Inputs: billingAccountName (required), lookbackDays, thresholdPercentage, projectId.
gcp-billing-get-account-detailsGet Billing Account DetailsA
Retrieve detailed information about a specific Google Cloud billing account
Inputs: billingAccountName (required).
gcp-billing-get-project-infoGet Project Billing InformationA
Retrieve billing configuration and status for a Google Cloud project
Inputs: projectId.
gcp-billing-list-accountsList Billing AccountsA
List all Google Cloud billing accounts accessible to the user
Inputs: pageSize, pageToken, filter.
gcp-billing-list-projectsList Billing Account ProjectsA
List all projects associated with a specific Google Cloud billing account
Inputs: billingAccountName (required), pageSize, pageToken.
gcp-billing-list-servicesList Google Cloud ServicesB
List all available Google Cloud services for billing and cost analysis
Inputs: pageSize, pageToken.
gcp-billing-list-skusList Service SKUsB
List all SKUs (Stock Keeping Units) and pricing information for a Google Cloud service
Inputs: serviceId (required), pageSize, pageToken, currencyCode.
gcp-billing-service-breakdownGet Service Cost BreakdownC
Get detailed cost breakdown by Google Cloud service with usage and SKU information
Inputs: billingAccountName (required), projectId, timeRange.
gcp-error-reporting-analyse-trendsD
Inputs: no named parameters.
gcp-error-reporting-get-group-detailsD
Inputs: no named parameters.
gcp-error-reporting-list-groupsD
Inputs: no named parameters.
gcp-iam-analyse-permission-gapsAnalyse Permission GapsC
Compare current permissions against required permissions for specific operations and identify gaps
Inputs: requiredPermissions (required), project, operationDescription.
gcp-iam-get-project-policyGet Project IAM PolicyB
Retrieve the IAM policy for a Google Cloud project
Inputs: project, requestedPolicyVersion.
gcp-iam-list-deployment-servicesList Available Deployment ServicesB
List all GCP services with pre-defined deployment permission sets
Inputs: no named parameters.
gcp-iam-test-project-permissionsTest Project IAM PermissionsA
Test which permissions the current caller has on a Google Cloud project
Inputs: permissions (required), project.
gcp-iam-test-resource-permissionsTest Resource-Specific IAM PermissionsA
Test which permissions the current caller has on specific Google Cloud resources
Inputs: resource (required), permissions (required).
gcp-iam-validate-deployment-permissionsValidate Deployment PermissionsA
Check if current caller has required permissions for deploying to common GCP services
Inputs: service (required), project, includeOptional.
gcp-logging-query-logsQuery LogsB
Query Google Cloud Logs with custom filters. Searches across all payload types (text, JSON, proto) and metadata fields.
Inputs: filter (required), limit.
gcp-logging-query-time-rangeQuery Logs by Time RangeA
Query Google Cloud Logs within a specific time range. Supports relative times (1h, 2d) and ISO timestamps.
Inputs: startTime (required), endTime, filter, limit.
gcp-logging-search-comprehensiveComprehensive Log SearchC
Search across all log fields including textPayload, jsonPayload, protoPayload, labels, HTTP requests, and metadata. Provides maximum context.
Inputs: searchTerm (required), timeRange, severity, resource, +1 more.
gcp-monitoring-list-metric-typesD
Inputs: filter, pageSize, timeout.
gcp-monitoring-query-metricsD
Inputs: filter (required), startTime (required), endTime, alignmentPeriod.
gcp-monitoring-query-natural-languageD
Inputs: query (required), startTime, endTime, alignmentPeriod.
gcp-profiler-analyse-performanceD
Inputs: no named parameters.
gcp-profiler-compare-trendsD
Inputs: no named parameters.
gcp-profiler-list-profilesD
Inputs: no named parameters.
gcp-spanner-execute-queryD
Inputs: sql (required), instanceId, databaseId, params.
gcp-spanner-list-databasesD
Inputs: instanceId (required).
gcp-spanner-list-instancesD
Inputs: _dummy.
gcp-spanner-list-tablesD
Inputs: instanceId, databaseId.
gcp-spanner-query-countD
Inputs: instanceId, databaseId, queryType, status, +3 more.
gcp-spanner-query-natural-languageD
Inputs: query (required), instanceId, databaseId.
gcp-trace-find-from-logsD
Inputs: filter (required), projectId, limit.
gcp-trace-get-traceD
Inputs: traceId (required), projectId.
gcp-trace-list-tracesD
Inputs: projectId, filter, limit, startTime.
gcp-trace-query-natural-languageD
Inputs: query (required), projectId.
gcp-utils-get-project-idGet Project IDA
Get the current Google Cloud project ID and recent project history
Inputs: no named parameters.
gcp-utils-set-project-idSet Project IDB
Set the default Google Cloud project ID to use for all operations
Inputs: project_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 40 tools
Tools are grouped by GCP service domains (billing, IAM, logging, monitoring, profiler, Spanner, trace, utils), which reduces ambiguity within each group, but there is overlap across groups. For example, multiple tools handle queries (gcp-logging-query-logs, gcp-monitoring-query-metrics, gcp-spanner-execute-query) without clear boundaries in their descriptions, and some tools like gcp-billing-analyse-costs and gcp-billing-service-breakdown could be confused for similar purposes. The domain grouping helps, but the sheer number of tools creates potential for misselection.
Tool names follow a consistent pattern of gcp-<service>-<action>-<target> with hyphens, making them predictable and readable. Minor deviations exist, such as gcp-utils-get-project-id using 'utils' instead of a service name and some names being more verbose (e.g., gcp-billing-detect-anomalies vs. gcp-trace-get-trace), but overall the naming is highly consistent across the set.
With 40 tools, the count is excessive for a single server, even given the broad scope of GCP billing and monitoring. This feels heavy and unwieldy, likely overwhelming for agents and users. A more focused approach with fewer, more generalized tools or splitting into multiple servers would be more appropriate, as the current scope spans multiple distinct domains beyond just billing and monitoring.
The server covers multiple GCP domains (billing, IAM, logging, monitoring, profiler, Spanner, trace, utils) with basic CRUD-like operations, but there are notable gaps. For example, in billing, tools exist for analysis and listing, but update or delete operations are missing; in monitoring and profiler, many tools lack descriptions, making it hard to assess coverage. The inclusion of unrelated services like Spanner suggests scope creep rather than a complete surface for the stated purpose.
Related MCP Connectors
FinOps assistant: query AWS, GCP and Azure cost, commitments, budgets and reports.
Ask about AWS, Azure, GCP, OpenAI, Anthropic and Snowflake costs, budgets, and anomalies.
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.
Query cloud, AI and SaaS spend across 25+ providers: costs, budgets, anomalies, unit economics.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact with Google Cloud Platform services for log analysis and root cause investigation. Provides tools to query Cloud Logging, detect error patterns, and perform real-time log streaming across multiple GCP projects.MIT
- AlicenseCqualityDmaintenanceEnables AI assistants to interact with Google Cloud Platform resources through natural language queries. Supports querying and managing GCP services like Compute Engine, Cloud Storage, BigQuery, and more across multiple projects and regions.9MIT
- FlicenseNot gradedqualityDmaintenanceEnables cost optimization and financial operations for Google BigQuery through natural language interactions. Provides insights into BigQuery spending, usage patterns, and cost management recommendations.-
- AlicenseBqualityDmaintenanceEnables interaction with Google Cloud Platform services through gcloud CLI, supporting operations like querying logs, checking Cloud Run status, managing secrets, executing Cloud SQL queries, and monitoring billing information.1123 npm1MIT