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

Use TrueFoundry with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Universal LLM Gateway & ML deployment hub: invoke 1000+ proxy models and manage MCP service instances natively.

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 · 8 capabilities

The complete TrueFoundry capability set.

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

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 8 available through TrueFoundry.

  1. 01

    Truefoundry generate embeddings

    Calculate semantic vectors securely using the unifed abstraction

  2. 02

    Truefoundry get mcp server info

    Extract exact JSON metadata of one registered TrueFoundry capability schema

  3. 03

    Truefoundry list gateway models

    List all accessible foundation models from the TrueFoundry unified AI gateway

  4. 04

    Truefoundry list mcp servers

    Extract registry mapping of all available logical MCP Capabilities in TrueFoundry

Capability set02 / 02

05-08

4 capabilities in this set.

Part of 8 available through TrueFoundry.

  1. 05

    Truefoundry deploy mcp server

    Spawn a new backend container logical process using TrueFoundry service mesh

  2. 06

    Truefoundry get deployment status

    Emit detailed metric states on the orchestration matrix bounds

  3. 07

    Truefoundry list deployments

    Monitor the existing array of running backend topologies mapped to the team

  4. 08

    Truefoundry run gateway chat

    G., openai/gpt-4o) mapping the true chat parameter to the gateway. Perform inference explicitly pushing a model query string through TrueFoundry

Observed, not estimated

870ms average. Fast in production.

TrueFoundry is checked daily against the live service.

Daily averagePeak 1148ms
Aug 20Today
Fastest day
719ms
Slowest day
1148ms
14-day trend
Slowing+24%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 8 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 TrueFoundry, so you can see the experience inside your AI.

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

TrueFoundry Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_f00nYwHsDWFv4EirgRZbXCnvKYC62empWE9xeumU/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 — TrueFoundry capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "truefoundry-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_f00nYwHsDWFv4EirgRZbXCnvKYC62empWE9xeumU/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 TrueFoundry owners ask.

  • 01

    Can I route conversational streams directly via the AI agent using the Universal Gateway?

    Yes! You can orchestrate inferences parsing run_gateway_chat providing dedicated string formats mapping natively any enabled model.

  • 02

    Is it possible to monitor crashed services or container states?

    Absolutely. Target the instance ID and emit get_deployment_status explicitly bounding execution limits and fetching live log matrices.

  • 03

    Are the deployment configuration variables isolated upon server launch?

    Yes, using deploy_mcp_server dynamically provisions encapsulated boundaries. You stringify environment tokens seamlessly obscuring values into active runtimes only.

Explore

More in AI Frontier

Suggestions