An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Portkey 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. Control LLM costs and monitor every model call through your agent.

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 · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Portkey.

  1. 01

    Export logs

    This capability exports AI gateway logs for external analysis or compliance. You can filter by date, model, or user to get a download URL or export ID.

  2. 02

    Get log details

    This capability retrieves deep debugging information for a specific log entry. You need the log ID from a previous list command to use it.

  3. 03

    Get virtual keys

    This capability lists all virtual API keys managed by Portkey. It shows provider targets, current usage, and status to help you audit key limits.

  4. 04

    List configs

    This capability returns all gateway configurations stored in Portkey. Use it to see how your LLM requests are being routed or to audit gateway behavior.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Portkey.

  1. 05

    List logs

    This capability pulls recent AI gateway logs and traces. It provides timestamps, model names, token usage, latency, and costs.

  2. 06

    List models

    This capability shows all LLM models supported by the Portkey gateway. It lists provider names and supported endpoints like chat or embeddings.

  3. 07

    List policies

    This capability lists all budget and usage policies. It shows policy names, current consumption, and which users or keys are affected.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Portkey.

  1. 08

    Submit feedback

    This capability submits user feedback like Likes or Dislikes for a specific response. It uses a log ID to help you build RLHF datasets.

  2. 09

    Create policy

    This capability creates a new budget or usage policy. You can set USD or token limits for specific users or virtual keys.

  3. 10

    Delete policy

    This capability removes an existing budget or usage policy using its ID.

Real work

What teams actually run

01

Budget Enforcement

Set a $500 limit for a specific project to ensure costs stay within bounds.

02

Latency Debugging

Identify which model calls are slow by reviewing specific log details.

03

Compliance Auditing

Generate log exports for the previous week to satisfy security requirements.

04

Model Optimization

Compare costs and performance across different models using gateway logs.

Automate a task

Put Portkey 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

Portkey 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 Portkey 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

880ms average. Fast in production.

Portkey is checked daily against the live service.

Daily averagePeak 995ms
Oct 3Today
Fastest day
720ms
Slowest day
995ms
14-day trend
Stable0%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 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 Portkey, so you can see the experience inside your AI.

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

Portkey Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_BpHtQMK896fkGyepmah9cM552NpibU6fUP5BakNG/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 — Portkey capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "portkey-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_BpHtQMK896fkGyepmah9cM552NpibU6fUP5BakNG/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 Portkey in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Portkey owners hand off.

This MCP is built for teams managing high-volume LLM workloads across multiple providers.

  • 01

    AI Platform Engineers

    They use the agent to monitor gateway health and optimize routing.

  • 02

    FinOps Analysts

    They use the agent to track token spend and enforce budget limits.

  • 03

    LLM Ops Teams

    They use the agent to debug latency and manage model configurations.

FAQ

Questions Portkey owners ask.

  • 01

    How do I monitor my LLM costs with this MCP?

    You can ask your AI agent to list recent logs or check specific usage patterns to see token spend and costs.

  • 02

    Can I limit spending for specific teams?

    Yes, you can use the agent to create budget policies that restrict usage based on USD or token counts for specific virtual keys.

  • 03

    Which AI clients can I use with Portkey?

    You can use this MCP with any compatible client, including Claude, Cursor, Windsurf, and VS Code.

  • 04

    Does this work with multiple LLM providers?

    Yes, the Portkey gateway provides unified observability across providers like OpenAI, Anthropic, and Google.

  • 05

    How do I debug a specific failed AI request?

    You can use the agent to retrieve detailed information about a specific log entry using its log ID.

  • 06

    Which LLM providers does Portkey support?

    Portkey supports 1,600+ LLMs including OpenAI, Anthropic, Google, Mistral, Azure OpenAI, AWS Bedrock, Cohere, Hugging Face, and many more. Use the list_models capability to see the full catalog available via your gateway.

  • 07

    How does Portkey help control AI costs?

    Portkey provides granular visibility into token usage, latency, and costs per model, team, or virtual key. You can create budget policies with hard limits to prevent runaway spending. The gateway also supports caching to reduce duplicate calls and fallbacks to cheaper models when appropriate.

  • 08

    Can I track feedback on AI responses?

    Yes! Portkey allows you to submit Like/Dislike feedback for any logged LLM call. This data helps improve model selection, evaluate agent performance, and build RLHF datasets for fine-tuning.

Explore

More in AI Frontier

Suggestions

Connect Portkey to Claude, Cursor, ChatGPT & more