Connect
Optimize
Secure
1Password MCP Server
for AI Agents
Production-ready 1Password MCP server with extensible actions — plus built-in authentication, security, and optimized execution.
1Password MCP Server
Built by 
StackOne
StackOne 
Coverage
14 Agent Actions
Create, read, update, and delete across 1Password — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your 1Password MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every 1Password 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 1Password call.
Tools Discovery →What is the 1Password MCP Server?
A 1Password MCP server lets AI agents read and write 1Password data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's 1Password MCP server ships with 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 1Password MCP Tools and Actions
Every action from 1Password's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
API Activitys
- List API Activity
Retrieve API request activity logs from the Connect server
Files
- List Files
Retrieve all files attached to an item
File Details
- Get File Details
Retrieve metadata and optionally content of a specific file
File Contents
- Download File Content
Download the binary content of a file
Heartbeats
- Get Heartbeat
Check if the Connect server is alive and responsive
Server Healths
- Get Server Health
Retrieve Connect server health status and dependencies
Prometheus Metrics
- Get Prometheus Metrics
Retrieve Prometheus metrics from the Connect server
Items
- Create Item
Create a new item in a vault
- List Items
Retrieve all items within a specific vault
- Get Item
Retrieve detailed information about a specific item
- Delete Item
Delete an item from a vault
Replace Items
- Replace Item
Replace an existing item with new data
Vaults
- List Vaults
Retrieve all vaults accessible by the Connect server
- Get Vault
Retrieve detailed information about a specific vault
Set Up Your 1Password MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to 1Password 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>"
]
}
}
}More Security MCP Servers
Cloudflare
137+ actions
OneLogin
109+ actions
Sentinel XS
69+ actions
Microsoft Entra ID
67+ actions
Drata
57+ actions
JumpCloud
53+ actions
Rippling
37+ actions
1Password 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
1Password MCP Server FAQ
1Password MCP server vs direct API integration — what's the difference?
A 1Password MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling 1Password. A 1Password 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 1Password at runtime. StackOne provides both.
How does 1Password authentication work for AI agents?
1Password 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 1Password account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are 1Password MCP tools vulnerable to prompt injection?
Yes — 1Password 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 1Password agent and how do I avoid it?
Context bloat happens when 1Password tool schemas and API responses eat your 1Password agent's memory, preventing it from reasoning effectively. A single 1Password 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 1Password agent can access?
Yes — you can limit which actions your 1Password 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 1Password MCP server?
Yes — you can create custom agent actions for your 1Password MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research 1Password's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a 1Password MCP server?
Skip a 1Password MCP server if your integration is purely software-to-software — direct 1Password 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 1Password actions at runtime.
What AI frameworks and AI clients does the StackOne 1Password MCP server support?
The StackOne 1Password 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.