An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Aserto 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. Test permissions and audit access decisions instantly.

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 · 7 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 7 available through Aserto.

  1. 01

    Authz is

    Use authz_is to determine if a specific user identity is authorized to perform an action based on policy and resource context.

  2. 02

    Get decision log

    If you need a signed download URL for a specific log object, use get_decision_log.

  3. 03

    Query decision logs

    To check the last N decisions recorded, run query_decision_logs.

  4. 04

    Authz decisiontree

    Get decision tree values across all policy modules using authz_decisiontree for deep policy inspection or UI logic.

Capability set02 / 02

05-07

3 capabilities in this set.

Part of 7 available through Aserto.

  1. 05

    Authz query

    Execute a general Rego query against the Authorizer using authz_query to inspect policy data or evaluate complex logic.

  2. 06

    Control plane exec

    Send commands to a connected Edge Authorizer by calling control_plane_exec to sync policy instances or directories.

  3. 07

    List decision logs

    To see what decision logs are available, run list_decision_logs.

Real work

What teams actually run

01

Debugging a Permission Issue

A user reports they can't access a document. You ask the agent to run authz_is with the user's ID and the resource context to pinpoint the exact policy failure.

02

Compliance Audit

You need to prove that all users in a specific group can only read certain data. You use query_decision_logs to pull the last N decisions for that group.

03

Policy Review

Before deploying a new policy, you use authz_decisiontree to map out all the decision paths and ensure no edge cases were missed.

04

System Maintenance

You need to force a policy update on a remote edge location. You use control_plane_exec to send the necessary synchronization command.

Automate a task

Put Aserto 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

Aserto 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 Aserto 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

996ms average. Fast in production.

Aserto is checked daily against the live service.

Daily averagePeak 1152ms
Oct 3Today
Fastest day
821ms
Slowest day
1152ms
14-day trend
Improving-16%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 7 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 Aserto, so you can see the experience inside your AI.

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

Aserto Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_XOpJU2PJe7LAxPuGtGU6XTuW4mAiWsbg1RviddXw/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 — Aserto capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "aserto-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_XOpJU2PJe7LAxPuGtGU6XTuW4mAiWsbg1RviddXw/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 Aserto in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Aserto owners hand off.

This MCP is essential for technical roles that deal with complex access rules. Security Engineers use it to quickly test policy changes and verify authorization logic without writing manual API calls. Backend Developers integrate and debug fine-grained access control during the development lifecycle. Compliance Officers use it to audit decision logs and confirm policies meet regulatory requirements.

  • 01

    Security Engineers

    Test policy changes and verify authorization logic without leaving your chat client.

  • 02

    Backend Developers

    Integrate and debug fine-grained access control (FGAC) directly into your development workflow.

  • 03

    Compliance Officers

    Audit decision logs and verify that access control policies meet strict regulatory requirements.

FAQ

Questions Aserto owners ask.

  • 01

    What is Rego, and why do I need this MCP?

    Rego is the policy language used by Aserto. This MCP lets your AI agent execute custom Rego queries using authz_query. This means you can inspect complex policy data and evaluate logic without needing to write the Rego code yourself.

  • 02

    Can I check if a user has permission without writing code?

    Yes. You use the authz_is capability. You simply ask your agent if a specific user is authorized to perform an action on a resource, and it returns a true/false decision.

  • 03

    How do I check past access decisions?

    You first run list_decision_logs to see what log objects are available. Then, you use query_decision_logs or get_decision_log to retrieve the specific audit records you need.

  • 04

    Is this MCP only for reading data?

    No. Beyond reading, you can send commands to connected Edge Authorizers using control_plane_exec to actively manage and synchronize policy instances.

  • 05

    What kind of policies does this handle?

    This MCP handles fine-grained access control (FGAC) policies. This means it manages permissions down to the level of specific resources and actions, not just broad user roles.

  • 06

    How do I verify a specific permission for a user?

    Use the authz_is capability. You need to provide the identity context (user), the policy context (the path to the rule), and any relevant resource context to get a boolean decision.

  • 07

    Can I execute complex Rego logic through the agent?

    Yes! The authz_query capability allows you to run any valid Rego query against your authorizer, enabling you to inspect data or evaluate custom logic on the fly.

  • 08

    Is it possible to trigger a policy sync on an Edge Authorizer?

    Yes. Use the control_plane_exec capability with the instance ID and the appropriate command (e.g., {"discovery": {}}) to manage your connected authorizers.

Explore

More in Developer Tools

Suggestions

Connect Aserto to Claude, Cursor, ChatGPT & more