An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Keywords AI 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. Track your API costs and model performance directly through your AI client.

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 · 11 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 11 available through Keywords AI.

  1. 01

    Check keywordsai status

    Verify that the API is connected and running. Use this to troubleshoot connectivity issues.

  2. 02

    Get request

    Fetch details for a specific API request. This is useful for deep diving into a single call's data.

  3. 03

    Get usage stats

    Get detailed usage statistics. Use this to monitor how your tokens and requests are being consumed.

  4. 04

    Get user

    Retrieve specific user details. This capability provides information about the account holder.

Capability set02 / 03

05-08

4 capabilities in this set.

Part of 11 available through Keywords AI.

  1. 05

    List alerts

    View your active monitoring alerts. This helps you see if any thresholds have been crossed.

  2. 06

    List models

    See the full catalog of available LLM models. Use this to find which models you can call.

  3. 07

    List requests by model

    Filter request logs by a specific model. This helps you isolate performance or cost data for one model.

  4. 08

    List requests

    Access your LLM API request logs. Use this to see a history of all calls made through the gateway.

Capability set03 / 03

09-11

3 capabilities in this set.

Part of 11 available through Keywords AI.

  1. 09

    List users

    Get a list of team members. Use this to manage or view activity across your organization.

  2. 10

    Get analytics

    Pull data from your analytics dashboard. This provides a high level view of your system performance.

  3. 11

    Get credits

    Check your current credit balance. Use this to see how much budget remains for your LLM calls.

Real work

What teams actually run

01

Budget Monitoring

Ask your agent how many credits you have left before starting a large scale testing run.

02

Latency Troubleshooting

Identify if a specific model is experiencing high latency by requesting analytics.

03

Error Investigation

Pull specific request logs to see why an API call failed without leaving your editor.

04

Model Comparison

Compare the cost and performance of different models by filtering request logs.

Automate a task

Put Keywords AI 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

Keywords AI 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 Keywords AI 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

852ms average. Fast in production.

Keywords AI is checked daily against the live service.

Daily averagePeak 1041ms
Oct 3Today
Fastest day
632ms
Slowest day
1041ms
14-day trend
Improving-11%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 11 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 Keywords AI, so you can see the experience inside your AI.

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

Keywords AI Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_R4VkEIrwLVvP7dLw0Fdy9vfjO7WqxWYeI2hDwlBU/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 — Keywords AI capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "keywords-ai-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_R4VkEIrwLVvP7dLw0Fdy9vfjO7WqxWYeI2hDwlBU/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 Keywords AI in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Keywords AI owners hand off.

This MCP is built for developers and engineers managing LLM-powered applications who need real time visibility into their API usage.

  • 01

    AI Engineers

    They use the agent to monitor model performance and latency during testing.

  • 02

    DevOps Engineers

    They hand off the task of checking API status and error alerts to their AI client.

  • 03

    Product Managers

    They use the agent to quickly pull cost and usage reports for budget tracking.

FAQ

Questions Keywords AI owners ask.

  • 01

    How do I see my remaining API credits?

    You can simply ask your AI client to show your current credit balance using the get_credits capability.

  • 02

    Can I check which models are currently available?

    Yes, you can ask your agent to list available models to see the full catalog.

  • 03

    How do I troubleshoot a failed API call?

    You can use the list_requests or get_request capabilities to pull the specific logs and details for that call.

  • 04

    Does this MCP work with my existing AI capabilities?

    Yes, it works with any MCP-compatible client including Claude, Cursor, and Windsurf.

  • 05

    Can I monitor my team's usage?

    Yes, you can use the list_users capability to see team members and their activity.

  • 06

    Can my AI track LLM costs?

    Yes. get_credits shows your balance, get_usage_stats breaks down costs by model and time period.

  • 07

    Can I filter request logs by model?

    Yes. list_requests_by_model returns only requests made to a specific LLM.

  • 08

    What analytics are available?

    get_analytics provides cost trends, latency percentiles, error rates, and token usage over time.

Explore

More in Developer Tools

Suggestions

Connect Keywords AI to Claude, Cursor, ChatGPT & more