How to Use the Humanloop (LLM Prompt Management API) MCP in VS Code Copilot

Q: How do I set up the Humanloop (LLM Prompt Management API) MCP Server for my team in VS Code Copilot?

Create a .vscode/mcp.json file in your repository root and add the server configuration. Once committed, every developer on your team using VS Code Copilot gains instant access to the MCP tools.

Q: Can I test prompt variations in VS Code Copilot using the Humanloop (LLM Prompt Management API)?

Yes, you can run prompts using the callpromptstream tool. This streams the model response directly into your Copilot chat panel, letting you verify formatting and behavior against live configurations.

Q: Can I edit prompt metadata from the chat interface?

Yes. The updatepromptversion tool allows you to rename or update descriptions for specific prompt versions directly from your Copilot chat window, keeping your registry organized.

Manage and deploy Humanloop prompts directly from VS Code Copilot, keeping your entire engineering team aligned in one editor.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Humanloop (LLM Prompt Management API) MCP to VS Code Copilot

Create your Vinkius account to connect Humanloop (LLM Prompt Management API) to VS Code Copilot and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Humanloop (LLM Prompt Management API) with VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage deployments via VS Code Copilot

The `deploy_prompt` tool sets specific prompt configurations live for environments like production or staging right from your VS Code Copilot chat. By adding this MCP Server to your workspace, your entire engineering team shares the same deployment tools. If a deployment needs to be rolled back, the `remove_deployment` tool clears the active prompt version from the environment. This keeps your production releases safe and managed directly from your shared editor environment.

Audit prompt versions in the editor

The `list_prompt_versions` tool fetches the history of prompt variations directly into VS Code Copilot. You can review past changes and parameters side by side with your application code before deploying updates. This eliminates the need to cross-reference Git history with a web-based dashboard. You see exactly who changed what, and when, without leaving your active coding workspace.

Track prompt performance and telemetry

The `log_to_prompt` tool records model generations and execution logs directly to your Humanloop dashboard from VS Code Copilot. Your agent logs the inputs and outputs of your local runs, ensuring your telemetry is accurate. You can also use the `update_monitoring` tool to toggle evaluators for these logs. This lets you control your active monitoring pipelines directly from the editor during test runs.

Setup guide

Set up Humanloop (LLM Prompt Management API) MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Humanloop (LLM Prompt Management API) MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Humanloop (LLM Prompt Management API) tools listed. Try asking: "List my recent Humanloop (LLM Prompt Management API) transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "humanloop-llm-prompt-management-api-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Humanloop. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Humanloop (LLM Prompt Management API) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Humanloop (LLM Prompt Management API) MCP in VS Code Copilot

Create a `.vscode/mcp.json` file in your repository root and add the server configuration. Once committed, every developer on your team using VS Code Copilot gains instant access to the MCP tools.

Yes, you can run prompts using the `call_prompt_stream` tool. This streams the model response directly into your Copilot chat panel, letting you verify formatting and behavior against live configurations.

The MCP server displays all environments and their currently deployed versions when you invoke the `list_prompt_environments` tool. This gives your team immediate visibility into what is live in staging or production.

Yes. The `update_prompt_version` tool allows you to rename or update descriptions for specific prompt versions directly from your Copilot chat window, keeping your registry organized.

The MCP architecture runs your credentials locally in an isolated sandbox, ensuring your API keys are never exposed to external networks. Prompt payloads, logs, and model generations are transmitted securely using direct HTTPS protocols to prevent data leaks.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript