An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Runlayer to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Govern your entire MCP ecosystem through natural language.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 27 capabilities

We ship only the actions that matter.

Capability set01 / 07

01-04

4 capabilities in this set.

Part of 27 available through Runlayer.

  1. 01

    Update skill

    Refines existing skill definitions or documentation. You only need to provide the specific fields you want to change along with the skill ID.

  2. 02

    Create agent

    Onboards new AI agents to your control plane. You can specify the agent type, such as Claude Desktop or Cursor, and assign specific MCPs and policies during setup.

  3. 03

    Create policy

    Sets up new security or access rules. This allows you to restrict which agents can touch specific MCPs or define strict audit requirements.

  4. 04

    Create skill

    Registers a new reusable capability for your agents. You can define input and output schemas and link it to specific MCPs.

Capability set02 / 07

05-08

4 capabilities in this set.

Part of 27 available through Runlayer.

  1. 05

    Delete agent

    Removes an AI agent from the system. This action automatically disconnects the agent from all its assigned MCPs and policies.

  2. 06

    Delete mcp server

    Deletes an MCP from your inventory. Doing this also strips all associated policies and agent connections.

  3. 07

    Delete policy

    Removes a security policy. Once deleted, any resources that were governed by that policy are no longer restricted by those specific rules.

  4. 08

    Delete skill

    Deletes a specific skill. This removes the capability from your agent list without affecting the underlying MCP capabilities.

Capability set03 / 07

09-12

4 capabilities in this set.

Part of 27 available through Runlayer.

  1. 09

    Get agent

    Retrieves detailed configuration and access patterns for a specific agent using its ID.

  2. 10

    Get audit logs

    Fetches complete audit trails including timestamps, actors, and actions. Use this to investigate security incidents or pull compliance reports.

  3. 11

    Get mcp server

    Provides deep technical details and security status for a specific MCP using its UUID.

  4. 12

    Get organization

    Returns your organization's configuration and a high level view of your entire MCP ecosystem.

Capability set04 / 07

13-16

4 capabilities in this set.

Part of 27 available through Runlayer.

  1. 13

    Get scan results

    Retrieves the findings from a previously run MCP sweep scan. This is how you see what shadow AI was discovered.

  2. 14

    Get skill

    Fetches the configuration and dependency details for a specific skill.

  3. 15

    List API keys

    Shows all API keys in your organization. This helps you find unused keys or prepare for a rotation.

  4. 16

    List agents

    Provides a full list of registered agents, including their types, assigned skills, and current policy compliance status.

Capability set05 / 07

17-20

4 capabilities in this set.

Part of 27 available through Runlayer.

  1. 17

    List mcp servers

    Displays your entire inventory of registered MCPs, their status, and which agents are currently using them.

  2. 18

    List members

    Lists all users in your Runlayer organization to help you audit roles and account activity.

  3. 19

    List policies

    Shows all active security and access policies, including how many violations they have caught.

  4. 20

    List skills

    Lists all registered skills, showing their descriptions, associated MCPs, and how often they are used.

Capability set06 / 07

21-24

4 capabilities in this set.

Part of 27 available through Runlayer.

  1. 21

    Revoke API key

    Immediately invalidates an API key. Use this if a key is leaked or no longer needed.

  2. 22

    Run mcp sweep scan

    Triggers a scan across your organization to find unauthorized or shadow AI resources.

  3. 23

    Update agent

    Modifies an existing agent's configuration, such as changing its assigned skills or metadata.

  4. 24

    Update mcp server

    Updates an MCP's settings, such as changing its endpoint URL or rotating its credentials.

Capability set07 / 07

25-27

3 capabilities in this set.

Part of 27 available through Runlayer.

  1. 25

    Update policy

    Edits the rules of an existing security policy to refine access controls or audit requirements.

  2. 26

    Create API key

    Generates a new API key for your organization. You'll get the key value once, so save it immediately.

  3. 27

    Create mcp server

    Registers a new MCP by providing its name and connection details like the URL and auth method.

Real work

What teams actually run

01

Scaling AI Access

Onboard dozens of new agents with specific, pre-approved skill sets in seconds.

02

Security Auditing

Instantly pull logs to see exactly which agent accessed which MCP at a specific time.

03

Shadow AI Cleanup

Identify and remove unauthorized MCP endpoints that employees added without permission.

04

Credential Rotation

Update MCP connection details or rotate API keys through a simple chat command.

Automate a task

Put Runlayer to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Runlayer works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Runlayer to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

983ms average. Fast in production.

Runlayer is checked daily against the live service.

Daily averagePeak 1358ms
Oct 5Today
Fastest day
829ms
Slowest day
1358ms
14-day trend
Improving-25%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 27 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Runlayer, so you can see the experience inside your AI.

It does not authenticate your account with Runlayer. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Runlayer Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_PaTg4jiaCBAOZI6pcScShh9467XvfcKP4495NMGs/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Runlayer capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "runlayer-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_PaTg4jiaCBAOZI6pcScShh9467XvfcKP4495NMGs/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Runlayer in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Runlayer owners hand off.

Designed for organizations scaling AI deployment who need centralized oversight.

  • 01

    IT Security Teams

    Hand off policy enforcement and shadow AI discovery to the agent.

  • 02

    Platform Engineers

    Hand off MCP registration and infrastructure management to the agent.

  • 03

    Compliance Managers

    Hand off audit log retrieval and policy violation reporting to the agent.

FAQ

Questions Runlayer owners ask.

  • 01

    How do I manage my MCPs with Runlayer?

    You use your AI client to issue commands. Instead of using a web dashboard, you tell your agent to register, update, or delete MCPs.

  • 02

    Can I use this with Claude or Cursor?

    Yes. This MCP is designed to work with any MCP-compatible client, including Claude Desktop, Cursor, and VS Code.

  • 03

    How does it help with security?

    It allows you to define strict policies, run scans to find unauthorized AI usage, and maintain full audit logs of every action taken by an agent.

  • 04

    What happens if I delete an agent?

    The agent is immediately disconnected from all its assigned MCPs and any security policies it was subject to.

  • 05

    Is it easy to find unauthorized AI capabilities?

    Yes. You can trigger an MCP sweep scan, and your agent will report back any shadow AI or policy violations it finds.

  • 06

    Do I need a Runlayer enterprise subscription to use this MCP?

    Yes, this MCP server requires an active Runlayer organization with API access. Runlayer is an enterprise-grade control plane, so you need a valid organizational subscription. Contact Runlayer sales to get started and obtain your organization API key.

  • 07

    Can this MCP server detect unauthorized AI usage (shadow AI)?

    Yes! The run_mcp_sweep_scan capability initiates comprehensive shadow AI discovery across devices, detecting unauthorized MCP servers, OpenClaw installs, Skills, and agents. Results include policy violations and security risks across your organization's endpoints.

  • 08

    What types of AI agents does Runlayer support?

    Runlayer supports Claude Desktop, Cursor, VS Code with Copilot, Windsurf, and custom AI agents. Each agent type can be registered with specific security policies, assigned MCP servers, and monitored through the audit trail. New agent types can be added as custom integrations.

Explore

More in Friends

Suggestions

Connect Runlayer to Claude, Cursor, ChatGPT & more