Download PDFMarkdown Version
ClaudeChatGPTPerplexityGeminiMicrosoft CopilotRaycastMeta AIGrokZ.aiQwenKimi
DeepSeekMistralCursorVS CodeWindsurfJetBrainsClineLovableVercel AI SDKLangChain

Use Forefront with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Access Forefront AI models directly from your agent. generate chat completions, manage fine-tuning jobs, and collect LLM outputs with pipelines.

Included with plan

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

Complete set · 10 capabilities

The complete Forefront capability set.

These are the exact actions your AI can choose when you ask it to work with Forefront.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Forefront.

  1. 01

    Create pipeline dataset

    Create a dataset from a pipeline selection

  2. 02

    Create pipeline

    Create a new pipeline to collect LLM outputs

  3. 03

    Add pipeline data

    Add data samples to a pipeline

  4. 04

    List pipelines

    Returns a list of your pipelines

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Forefront.

  1. 05

    Create chat completion

    Pass messages array in chat-ml format. Creates a model response for the given chat conversation

  2. 06

    Create completion

    Pass a single prompt string. Creates a completion response for a given prompt

  3. 07

    Create fine tune

    Creates a fine-tuning job

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Forefront.

  1. 08

    Get pipeline

    Returns a pipeline object by ID

  2. 09

    Get pipeline count

    Get count of pipeline selection

  3. 10

    Get pipeline samples

    Get data samples for a pipeline selection

Observed, not estimated

925ms average. Fast in production.

Forefront is checked daily against the live service.

Daily averagePeak 1412ms
Aug 20Today
Fastest day
822ms
Slowest day
1412ms
14-day trend
Slowing+16%

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 Forefront, so you can see the experience inside your AI.

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

Forefront Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_9p3sy2z5j8vwdMtOomVYymmFfYsP4YghbaGI6v8C/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 — Forefront capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "forefront-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_9p3sy2z5j8vwdMtOomVYymmFfYsP4YghbaGI6v8C/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

FAQ

Questions Forefront owners ask.

  • 01

    How can I generate a model response using a chat conversation?

    You can use the create_chat_completion capability. Provide the model name and an array of messages in chat-ml format to receive the generated response.

  • 02

    Can I start a custom fine-tuning job directly from my agent?

    Yes! Use the create_fine_tune capability by specifying the name of your fine-tuned model, the baseModel, and the trainingDataset ID to begin training.

  • 03

    How do I collect LLM outputs using pipelines?

    First, create a pipeline using create_pipeline. Once created, you can use add_pipeline_data to log messages, user IDs, and custom metadata directly into that pipeline.

Explore

More in Developer Tools

Suggestions