惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

爱范儿
爱范儿
大猫的无限游戏
大猫的无限游戏
J
Java Code Geeks
MongoDB | Blog
MongoDB | Blog
Martin Fowler
Martin Fowler
GbyAI
GbyAI
Microsoft Azure Blog
Microsoft Azure Blog
Recent Announcements
Recent Announcements
F
Fortinet All Blogs
B
Blog
U
Unit 42
B
Blog RSS Feed
D
DataBreaches.Net
Google DeepMind News
Google DeepMind News
人人都是产品经理
人人都是产品经理
腾讯CDC
量子位
酷 壳 – CoolShell
酷 壳 – CoolShell
V
Visual Studio Blog
博客园 - 聂微东
MyScale Blog
MyScale Blog
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
博客园 - 三生石上(FineUI控件)
Engineering at Meta
Engineering at Meta

Blog on 1Password Blog

Why secure-by-design is an incentives problem, with Bob Lord | 1Password NIST and AI agents: 1Password’s approach to agent identity | 1Password Go beyond device health with External Checks in 1Password Device Trust | 1Password Natoma and 1Password help enterprises scale AI securely with governed agent access | 1Password New integrations between 1Password SaaS Manager and EPM | 1Password A first step toward post-quantum security | 1Password RSA 2026: Leading the way to secure agentic AI | 1Password How 1Password is Building a Culture of AI Fluency Through AI Champions | 1Password 1Password vs. Keeper Security: A comparison | 1Password 1Password vs. LastPass: Which is right for you? | 1Password The next layer of AI security | 1Password Building the next chapter of Go-to-Market in EMEA | 1Password Automating SOC workflows with 1Password Enterprise Password Manager | 1Password Automated Provisioning hosted by 1Password: A Simpler, Smarter Way to Manage Access | 1Password Introducing 1Password® Unified Access: Identity Security for Humans and Their AI Agents | 1Password Next-generation automated provisioning, without compromising zero-knowledge security | 1Password Bitwarden vs. 1Password: Which password manager is right for you? | 1Password Password Manager for Families, Enterprise & Business | 1Password | 1Password How to wrangle SaaS contract renewals | 1Password Stop trusting consumer browsers with work credentials | 1Password IAM stops at sign-in. Your credentials do not. | 1Password Your digital pit crew: a 10-minute pre-race security checklist | 1Password 1Password Device Trust is coming to EMEA | 1Password The identity transformation: Analyst and CIO insights | 1Password Why now is the moment to join 1Password Go-To-Market | 1Password Identity and Accountability in the Age of AI Agents | 1Password How 1Password secures agent architectures | 1Password 1Password becomes the first global partner to transact through Express Private Offers in AWS Marketplace | 1Password Start Learning on 1Password Academy | 1Password Expanding Programmatic Access to 1Password | 1Password
Secure MCP credentials with 1Password and Runlayer | 1Pas...
info@1password.com (Jeff Malnick) · 2026-03-20 · via Blog on 1Password Blog

We built 1Password® Unified Access to extend identity security beyond humans to the agents and machine workloads operating across your business. In practice, that means securing not just who gets access, but how agentic systems connect to tools, services, and data.

That makes the MCP gateway a critical control point. It sits between AI agents and the systems they need to reach, making it the natural place to enforce policy, visibility, and governance. But in many deployments, it also becomes the place where credentials accumulate, moving secrets out of the vault and into the platform.

That is the problem 1Password and Runlayer are solving together. With this integration, enterprises can keep their machine credentials in 1Password, resolve them only at runtime, and audit every fetch and rotation without exposing the secret itself.

If your team has adopted an MCP platform to centralize how AI agents access tools, you've probably solved one problem and created another.

Before the MCP platform, credentials were scattered across developer machines in plaintext config files:

Secure MCP credentials with 1Password and Runlayer, before the MCP platform, credentials were scattered across developer machines in plaintext config files:

After the MCP platform, those credentials shifted from the developer’s laptop into the platform’s database. This centralizes them, but still keeps them outside your vault. Exposure on the local machine decreases, while secrets sprawl and operational complexity increase. A better model is to keep these credentials alongside the rest of your secrets, in a system that is consistent, easy to use, and supports self-service for the AI builder.

MCP platforms shouldn’t become another place for secrets sprawl

Enterprises are using hundreds to thousands of upstream server connections like GitHub, Slack, Notion, Linear, and internal APIs. Each server needs at least one credential. When those credentials live outside the vault:

  • A platform compromise exposes every MCP server token at once.

  • There's no single source of truth for who changed what credential and when.

  • Enforcement of credential access policies lives outside a targeted, centralized solution.

As enterprises move from experimenting with AI tools to deploying them in production, this gap grows from a hygiene issue to a governance problem.

1Password keeps credentials in the vault, not the platform

As we worked with Runlayer on this integration, we held to the same security principles that guide all of our AI work:

  • Secrets stay secret. Credentials live exclusively in the customer's 1Password vault. Runlayer stores a reference, never the raw value.

  • Least privilege and minimum exposure. The secret exists in memory only for the duration of the request. Nothing persists on disk or in the gateway's database.

  • Full Auditability. Every secret fetch and every rotation is logged in 1Password and in Runlayer with hash-based traceability that never exposes the credential itself.

About the Runlayer AI control plane

Runlayer is the Enterprise Control Plane for MCP, Skills, and Agents. It sits between AI agents, IDEs, and MCP servers, proxying every tool call through a control plane that applies real-time security models and policies, logs complete audit trails, and centrally manages credentials. Think of it as the one layer for AI tool access, every MCP request flows through it, which makes it the natural place to securely inject credentials at runtime for agent workloads.

Secure the control point without creating a new secrets store

The integration uses a simple pattern: instead of pasting a raw API key into Runlayer's server configuration, you enter a 1Password secret reference. Runlayer resolves it at connection time.

Enter a 1Password reference instead of a raw key

In Runlayer's Server Inputs UI, enter an op:// reference for any credential field:

In Runlayer's Server Inputs UI, enter an op:// reference for any credential field:

The UI shows a blue 1Password badge next to the field and displays "Managed by 1Password" as the status. The reference format follows the standard 1Password convention: op://vault/item/field.

This reference is all Runlayer stores. No raw credentials touch Runlayer's database.

At connection time, Runlayer resolves the secret

When the MCP proxy handles a tool call, it scans transport headers for op:// references. For each match, it calls the 1Password SDK to resolve the live value and injects it into the upstream connection:

When the MCP proxy handles a tool call, it scans transport headers for op:// references. For each match, it calls the 1Password SDK to resolve the live value and injects it into the upstream connection:

The resolution supports prefixed values too. A header configured as Bearer op://MCP/GitHub/token resolves to Bearer ghp_actual_token_value - the prefix is preserved, only the op:// portion is replaced.

Once the upstream request completes, the secret is no longer in memory. No caching to disk, no storage in the database, no residual exposure.

Credential changes are picked up automatically

If someone rotates the credential in 1Password, Runlayer picks up the new value on the next connection. It detects changes by comparing the SHA-256 hashes of resolved values against prior fetches.

When a rotation is detected, Runlayer emits a secret_provider.rotated audit event with both the old and new credential hashes, enough to confirm the rotation happened without revealing the credential itself. The audit log entry reads: "New credential fetched from 1Password - zero downtime."

No config changes. No redeployments. No coordination between teams. Rotate in 1Password, and every agent picks up the new credential on its next request.

Runlayer's approach to AI credential management for MCPs aligns with how enterprises want to handle secrets - in the vault, resolved at runtime, with a full audit trail. The op:// pattern means credentials never leave 1Password until the exact moment they're needed."

Andy Berman, CEO of Runlayer

What's available today

  • op:// references in any MCP server credential field.

  • Live secret resolution at proxy time via the 1Password SDK.

  • Automatic rotation detection with zero downtime, hash comparison on every fetch.

  • Audit events for every secret fetch (secret_provider.fetched) and rotation (secret_provider.rotated).

  • UI badges showing which credentials are managed by 1Password.

  • Hash-based traceability, credential values are never logged, only their hashes.

What’s next for MCP security

This integration is the foundation for a deeper collaboration between 1Password and Runlayer. In the coming months, we plan to expand support for:

  • Coordinated rotation. Runlayer triggers rotation on a schedule or policy violation; 1Password updates the vault item automatically.

  • Full agent identity lifecycle. Creating an agent in Runlayer auto-creates a corresponding 1Password vault item; deleting archives it.

  • BYOV for OAuth tokens. Extend the op:// pattern beyond API keys to OAuth client secrets and refresh tokens managed through Runlayer's delegation flow.

Get started with 1Password and Runlayer

MCP server credentials belong in your vault. With this integration, getting them there takes one change: replace the raw value with an op:// reference.