Connect
Optimize
Secure
Google Cloud Security MCP Server
for AI Agents
Production-ready Google Cloud Security MCP server with 56 extensible actions — plus built-in authentication, security, and optimized execution.
Google Cloud Security MCP Server
Built by 
StackOne
StackOne 
Coverage
56 Agent Actions
Create, read, update, and delete across Google Cloud Security — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Google Cloud Security MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Google Cloud Security tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Google Cloud Security call.
Tools Discovery →What is the Google Cloud Security MCP Server?
A Google Cloud Security MCP server lets AI agents read and write Google Cloud Security data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Google Cloud Security MCP server ships with 56 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All Google Cloud Security MCP Tools and Actions
Every action from Google Cloud Security's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Folders
- Create Folder
Create a new folder
- List Folders
List folders under a parent resource
- Get Folder
Get details of a specific folder
- Search Folders
Search for folders using a query
- Update Folder
Update a folder
- Delete Folder
Delete a folder
Project IAM Policys
- Get Project IAM Policy
Get the IAM policy for a project
- Set Project IAM Policy
Set the IAM policy for a project
Organizations
- Get Organization
Get details of a specific organization
- Search Organizations
Search for GCP organizations
Projects
- Create Project
Create a new GCP project
- List Projects
List all accessible GCP projects
- Get Project
Get details of a specific GCP project
- Search Projects
Search for GCP projects using a query
- Update Project
Update a GCP project
- Delete Project
Delete a GCP project
Project Roles
- Create Project Role
Create a custom IAM role in a project
- List Project Roles
List all custom roles in a project
- Update Project Role
Update a custom IAM role in a project
- Delete Project Role
Delete a custom IAM role from a project
Service Account Keys
- Create Service Account Key
Create a new key for a service account
- List Service Account Keys
List all keys for a service account
- Get Service Account Key
Get details of a specific service account key
- Delete Service Account Key
Permanently delete a service account key
Secret Versions
- Add Secret Version
Add a new version with secret data
- List Secret Versions
List all versions of a secret
- Get Secret Version
Get metadata of a specific secret version
Secrets
- Create Secret
Create a new secret in a project
- List Secrets
List all secrets in a project
- Get Secret
Get metadata of a specific secret
- Update Secret
Update metadata of an existing secret
- Delete Secret
Permanently delete a secret and all its versions
Secret IAM Policys
- Get Secret IAM Policy
Get the IAM policy for a secret
- Set Secret IAM Policy
Set the IAM policy for a secret
Service Accounts
- Create Service Account
Create a new service account in a project
- List Service Accounts
List all service accounts in a project
- Get Service Account
Get details of a specific service account
- Update Service Account
Update the metadata of an existing service account
- Delete Service Account
Delete a service account from a project
Tag Keys
- List Tag Keys
List tag keys under a parent resource
- Get Tag Key
Get details of a specific tag key
Tag Values
- List Tag Values
List tag values under a tag key
- Get Tag Value
Get details of a specific tag value
Other (13)
- List Predefined Roles
List all predefined IAM roles
- Get Role
Get details of a specific IAM role
- Test Project IAM Permissions
Test which IAM permissions the caller has on a project
- Undelete Project Role
Restore a recently deleted custom IAM role
- Disable Service Account Key
Disable a service account key
- Enable Service Account Key
Enable a previously disabled service account key
- Access Secret Version
Access the payload of a secret version
- Enable Secret Version
Enable a previously disabled secret version
- Disable Secret Version
Disable a secret version
- Destroy Secret Version
Permanently destroy a secret version
- Disable Service Account
Disable a service account immediately
- Enable Service Account
Enable a previously disabled service account
- Undelete Service Account
Restore a recently deleted service account
Set Up Your Google Cloud Security MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Google Cloud Security in under 10 lines of code.
MCP Clients
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}Google Cloud Security MCP Server Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
Google Cloud Security MCP Server FAQ
Google Cloud Security MCP server vs direct API integration — what's the difference?
A Google Cloud Security MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Google Cloud Security. A Google Cloud Security MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Google Cloud Security at runtime. StackOne provides both.
How does Google Cloud Security authentication work for AI agents?
Google Cloud Security authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Google Cloud Security account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Google Cloud Security MCP tools vulnerable to prompt injection?
Yes — Google Cloud Security MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Google Cloud Security agent and how do I avoid it?
Context bloat happens when Google Cloud Security tool schemas and API responses eat your Google Cloud Security agent's memory, preventing it from reasoning effectively. A single Google Cloud Security query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Google Cloud Security agent can access?
Yes — you can limit which actions your Google Cloud Security agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Google Cloud Security MCP server?
Yes — you can create custom agent actions for your Google Cloud Security MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Google Cloud Security's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Google Cloud Security MCP server?
Skip a Google Cloud Security MCP server if your integration is purely software-to-software — direct Google Cloud Security API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Google Cloud Security actions at runtime.
What AI frameworks and AI clients does the StackOne Google Cloud Security MCP server support?
The StackOne Google Cloud Security MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.