Skip to main content
OneLayer is Runlayer’s unified MCP entrypoint for your organization. Instead of asking users to install and manage many separate MCP servers, OneLayer gives them one standard connection that can discover and run the tools they already have access to in Runlayer. It is designed for teams that want broad tool access without broad tool sprawl: one install surface for users, one governance layer for admins, and one place for models to discover what they can actually use.

​
What OneLayer is

OneLayer is a dynamic Runlayer plugin that automatically includes the connectors and skills a user can already access. Instead of exposing every tool up front, OneLayer uses a search-first flow:
  • search_tools finds relevant tools across the user’s accessible connectors
  • execute_tool runs the selected tool through the correct underlying connector
This keeps the tool surface smaller, reduces prompt bloat, and gives models a better chance of choosing the right tool instead of guessing from a giant flat list.
OneLayer does not grant new permissions. It only exposes the tools, skills, and platform capabilities the user already has access to through Runlayer.

​
What it enables

  • One MCP entrypoint for users instead of a long list of separate connector installs
  • Dynamic tool discovery across many connectors without flooding the model with schemas
  • Central policy enforcement because tool calls still flow through Runlayer controls
  • Auditability because usage stays inside the Runlayer path instead of bypassing it
  • Org-wide rollout for supported clients so admins can standardize setup
  • Org-level /runlayer skill available to every user in supported clients once OneLayer is enabled, so they can invoke Runlayer skills directly from a slash command without per-user setup

​
Why teams use it

OneLayer is useful when your team wants a default, opinionated way to use MCP safely at scale. Without it, users often end up with fragmented client setup, duplicate connectors, inconsistent tool availability, and unclear security boundaries. OneLayer fixes that by giving the organization a single approved layer for tool discovery and execution. In practice, that means:
  • admins can standardize the MCP experience across teams
  • users get a simpler setup and fewer things to configure
  • models can search for the right tool when needed instead of carrying every tool definition in context
  • Runlayer policies, approvals, and audit logs stay in the loop

​
How it works

When a user connects OneLayer in their AI client, the model sees a compact interface instead of hundreds of raw tools.
  1. The model calls search_tools with the task it wants to accomplish.
  2. OneLayer searches across the user’s accessible connectors and returns the most relevant tools.
  3. The model calls execute_tool on the selected tool, and Runlayer routes it to the correct connector.
This pattern is especially valuable for large organizations with many approved connectors, because it keeps the client configuration stable even as the underlying tool inventory grows.

​
Org-wide install

Open the OneLayer plugin page in Runlayer and click Add to Organization. Choose your provider — Anthropic or OpenAI — then follow the steps below. The dialog also includes an Auto Sync toggle. When enabled, the plugin is included when users run uvx runlayer setup sync, pushing the configuration to detected MCP clients automatically. See Automatic Configuration Provisioning for details.

​
Anthropic

1

Download runlayer.zip

Click Download zip.
2

Open Claude admin plugin settings

Go to Claude admin plugin settings and click Add plugin.Claude admin plugin settings with the Add plugins button
3

Select Upload a file

Choose Upload a file.Claude add plugins dialog with Upload a file selected
4

Upload the zip

Select runlayer.zip and click Upload.Claude upload plugin dialog with runlayer.zip ready to upload
5

Require access

Change user access to Required.Claude plugin settings with user access set to Required

​
OpenAI (ChatGPT / Codex)

1

Open Admin Connectors settings

Navigate to ChatGPT Admin Connectors and enable developer mode. In the Apps and Connectors section, click Create.
2

Register the MCP connector

Enter the MCP Server URL shown in the Runlayer dialog, provide a name (e.g. “OneLayer”), and click Create. Complete the OAuth authorization when prompted.
3

Publish the connector

After creation, publish the connector so it is available to your organization.
4

Upload skills

Click Download zip in the Runlayer dialog. Go to chatgpt.com/skills, upload runlayer.zip, and set sharing to Installed for everyone.