Connect
Optimize
Secure
Live 41 Actions
Google Directory MCP Server
for AI Agents
Connect your AI agent to StackOne's Google Directory MCP server and give it 41 MCP tools out of the box. Auth, tool execution, and security all managed.
Google Directory MCP Server
Built by 
StackOne
StackOne 
Coverage
41 Agent Actions
Create, read, update, and delete across Google Directory — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Google Directory MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Google Directory 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 Directory call.
Tools Discovery →What is the Google Directory MCP Server?
A Google Directory MCP server lets AI agents read and write Google Directory data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Google Directory MCP server ships with 41 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All Google Directory MCP Tools
Every action from Google Directory's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Unified Groups
- List Unified Groups
List unified groups in Google Directory.
- Get Unified Group
Get a unified Google Directory group by ID.
Unified Organizations
- List Unified Organizations
List unified organizations in Google Directory.
- Get Unified Organization
Get a unified Google Directory organization by ID.
Unified Roles
- List Unified Roles
List unified roles in Google Directory.
- Get Unified Role
Get a unified Google Directory role by ID.
Unified Users
- List Unified Users
List unified users in Google Directory.
- Get Unified User
Get a unified Google Directory user by ID.
Users
- Create User
Create a new user account
- List Users
Retrieve a paginated list of users in a domain
- Get User
Retrieve a user's properties
- Update User
Update a user's properties
- Delete User
Delete a user account
Groups
- Create Group
Create a new group
- List Groups
Retrieve all groups in a domain or for a user
- Get Group
Retrieve a group's properties
- Update Group
Update a group's properties
- Delete Group
Delete a group
Members
- List Members
Retrieve all members in a group
- Get Member
Retrieve a group member's properties
- Update Member
Update a group member's properties
Organizational Units
- Create Organizational Unit
Add a new organizational unit
- List Organizational Units
Retrieve all organizational units for an account
- Get Organizational Unit
Retrieve an organizational unit's properties
- Update Organizational Unit
Update an organizational unit's properties
- Delete Organizational Unit
Remove an organizational unit
Domains
- Create Domain
Create a domain for a customer account
- List Domains
Retrieve all domains associated with the customer account
- Get Domain
Retrieve a specific domain's properties
- Delete Domain
Delete a domain from a customer account
Other (11)
- Add Member To Group
Add a user or group to a group
- Get Unified Credentials
Get the current Google Directory connection's unified credentials and identity.
- List Unified Resource Types
List unified resource types in Google Directory.
- List Unified Resource Users
List unified resource users in Google Directory.
- Remove Member From Group
Remove a member from a group
- IAM Auth Test
Validate the current OAuth token and return the raw, unmapped Google tokeninfo JSON (email, scopes, expiry, audience, sub, access_type). Bypasses the unified IAM credentials schema — use this for debugging scope mismatches, token expiry, or revocation, not for normal app flows.
- Patch User
Update user using patch semantics
- Patch Group
Update group using patch semantics
- Patch Member
Update member using patch semantics
- Check Member Existence
Check if a user is a member of a group
- Patch Organizational Unit
Update org unit using patch semantics
Set Up Your Google Directory MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Google Directory in under 10 lines of code.
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>"
]
}
}
}Check More Security MCP Servers
Cloudflare
141+ actions
OneLogin
110+ actions
Auth0
87+ actions
Sentinel XS
69+ actions
Microsoft Entra ID
67+ actions
JumpCloud
65+ actions
Drata
57+ actions
Platform 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
MCP vs A2A: Architecture, Security, and When to Use Each
MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.
12 min
MCP vs API: What 200+ Connector Builds Taught Us
MCP wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.
14 min read
Google Directory MCP Server FAQ
Does StackOne have a Google Directory MCP server?
Yes. StackOne offers a hosted Google Directory MCP server with 41 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.
Google Directory MCP server vs direct API integration — what's the difference?
A Google Directory MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Google Directory. A Google Directory 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 Directory at runtime. StackOne provides both.
How does Google Directory authentication work for AI agents?
Google Directory 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 Directory account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Google Directory MCP tools vulnerable to prompt injection?
Yes — Google Directory 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 Directory agent and how do I avoid it?
Context bloat happens when Google Directory tool schemas and API responses eat your Google Directory agent's memory, preventing it from reasoning effectively. A single Google Directory 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 Directory agent can access?
Yes — you can limit which actions your Google Directory 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 Directory MCP server?
Yes — you can create custom agent actions for your Google Directory MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Google Directory's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Google Directory MCP server?
Skip a Google Directory MCP server if your integration is purely software-to-software — direct Google Directory 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 Directory actions at runtime.
What AI frameworks and AI clients does the StackOne Google Directory MCP server support?
The StackOne Google Directory 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.