cloud-support-mcp
Provides tools for managing Google Cloud support cases through the Google Cloud Support API v2, including case creation, updates, comments, search, and classification.
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., "@cloud-support-mcp create a support case for a BigQuery performance issue"
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.
Cloud Support MCP Server
MCP server for Google Cloud Support API v2.
Provides tools for managing Google Cloud support cases through AI assistants. Supports case creation, updates, comments, and search functionality.
Installation
npm install
npm run buildRelated MCP server: Resource Settings MCP Server
Authentication
Set up Google Cloud authentication:
# Service account
export GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account-key.json
# Or use gcloud
gcloud auth application-default loginUsage
npm startTools
list_support_cases- List support casesget_support_case- Get case detailssearch_support_cases- Search casessearch_case_classifications- Search classificationscreate_support_case- Create new casecreate_case_comment- Add commentupdate_support_case- Update caseclose_support_case- Close caseget_case_comments- Get commentslist_case_attachments- List attachments
Usage Examples
List Cases
{
"name": "list_support_cases",
"arguments": {
"parent": "projects/your-project-id",
"pageSize": 10
}
}Create Case
{
"name": "create_support_case",
"arguments": {
"parent": "projects/your-project-id",
"displayName": "Issue Summary",
"description": "Detailed description",
"classification": { "id": "technical-issue" }
}
}Search Case Classifications
Search for appropriate case classifications using display name patterns:
{
"name": "search_case_classifications",
"arguments": {
"query": "displayName:*BigQuery*",
"pageSize": 20
}
}Query Format Examples:
"displayName:*Billing*"- Find billing-related classifications"displayName:*Compute*"- Find Compute Engine classifications"displayName:*Storage*"- Find storage-related classifications
Note: Use asterisks (*) to wrap search terms in the displayName field. Direct text searches without the displayName: prefix may not work as expected.
Development
npm run dev # Development mode
npm test # Run tests
npm run lint # Code linting
npm run type-check # TypeScript validationRequirements
Node.js 18+
Google Cloud Support API access
Appropriate IAM permissions
Author
polar3130
License
MIT
Available Tools
10 toolsclose_support_caseA
Close an existing support case. Once closed, the case cannot be reopened.
Inputs: name (required).
create_case_commentA
Add a new comment to a support case for communication with Google Support.
Inputs: body (required), parent (required).
create_support_caseB
Create a new support case and associate it with a parent
Inputs: parent (required), priority (required), description (required), displayName (required), +5 more.
get_case_commentsB
Get comments and conversation history for a specific support case
Inputs: name (required).
get_support_caseA
Get detailed information about a specific support case
Inputs: name (required).
list_case_attachmentsB
List all attachments associated with a support case.
Inputs: parent (required), pageSize, pageToken.
list_support_casesC
List all support cases for a Google Cloud project or organization
Inputs: parent (required), filter, pageSize, pageToken.
search_case_classificationsA
Search and retrieve valid case classifications for creating support cases
Inputs: query, pageSize, pageToken.
search_support_casesC
Search support cases with various filters
Inputs: parent (required), query, state, priority, +2 more.
update_support_caseA
Update an existing support case. Only priority, displayName, and subscriberEmailAddresses can be updated.
Inputs: name (required), priority, updateMask, displayName, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
Each tool targets a distinct operation on support cases: listing, getting, searching, creating, updating, closing, comments, attachments, and classifications. No two tools have overlapping purposes; even list vs search are clearly differentiated by description.
Most tools follow a verb_noun pattern, but there is inconsistency in whether the noun is 'support_case' or 'case' (e.g., list_support_cases vs get_case_comments). This is a minor deviation that does not create confusion.
10 tools is a well-scoped count for a support case management server. Each tool covers a necessary function without redundancy or bloat, making the set easy to navigate.
The tool set covers the full lifecycle of support cases: create, read (list/get/search), update, close, comment, and list attachments. It also includes classification search, which is needed for creation. There are no obvious dead ends or missing critical operations.
Maintenance
Related MCP Connectors
MCP server for interacting with the Supabase platform
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
Read-only Google Search Console MCP server for AI assistants.
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMCP server to interact with Google produts.491MIT
- FlicenseNot gradedqualityDmaintenanceAn MCP Server that provides a natural language interface to Google Cloud Resource Settings API, enabling users to view and manage settings for Google Cloud resources through conversation.-
- FlicenseNot gradedqualityDmaintenanceThis MCP Server provides a natural language interface to interact with Google's Policy Analyzer API, allowing users to analyze policies and evaluate compliance through conversations.-
- FlicenseNot gradedqualityDmaintenanceModel Context Protocol server for Google Cloud Platform, enabling interaction with Resource Manager, Compute Engine, Cloud Storage, BigQuery, Pub/Sub, and Cloud Logging via natural language.3-