How to Use the Humanloop (LLM Prompt Management API) MCP in Claude

Q: How do I install the Humanloop (LLM Prompt Management API) MCP Server on Claude Desktop?

Open your claudedesktopconfig.json file and add the server configuration under the mcpServers key. Include your API key in the environment variables, then restart the Claude Desktop app to make all twelve tools available.

Q: Can I run dynamic evaluations using Humanloop (LLM Prompt Management API) in Claude Desktop?

Yes, you can trigger evaluations directly. Use the updatemonitoring tool to turn evaluators on or off for specific logs, allowing your agent to manage your testing pipelines straight from the desktop chat interface using the MCP tools.

Q: Can I clean up old prompt drafts from my chat?

Yes. The deletepromptversion tool allows you to remove unwanted versions from your registry. This keeps your workspace clean without requiring you to log into the cloud platform.

Deploy and test Humanloop prompts directly from your Claude Desktop chat without switching to your browser or terminal.

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 Claude Desktop

Create your Vinkius account to connect Humanloop (LLM Prompt Management API) to Claude Desktop 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy prompt updates via Claude Desktop

The `deploy_prompt` tool lets you assign a specific prompt version to environments like staging or production directly from your Claude Desktop interface via this MCP Server. Your agent handles the environment updates instantly, cutting out the manual clicks in the web UI. When you need to roll back or clear a configuration, the `remove_deployment` tool strips the active prompt from the target environment. You run these changes through the desktop chat window, keeping your configuration workflow in one place.

Test live prompts with instant feedback

The `call_prompt_stream` tool runs your active prompts and streams the responses right into your Claude Desktop chat panel. You see exactly how the model behaves with your dynamic variables without leaving your workspace. To keep your team's prompts organized, the `upsert_prompt` tool lets you create or modify prompt configurations on the fly. Your desktop agent handles the creation process, saving new variations directly to your central registry.

Audit version history and environments

The `list_prompt_versions` tool pulls the entire history of a prompt directly into Claude Desktop so you can compare changes side by side. You inspect the exact parameters of older configurations before making deployment decisions. You can also use the `list_prompt_environments` tool to check which versions are currently live across staging and production. It gives you a clear snapshot of your prompt distribution without forcing you to open external browser tabs.

Setup guide

Set up Humanloop (LLM Prompt Management API) MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Humanloop (LLM Prompt Management API) MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Humanloop (LLM Prompt Management API) MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under humanloop-llm-prompt-management-api-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 Claude Desktop

Open your `claude_desktop_config.json` file and add the server configuration under the `mcpServers` key. Include your API key in the environment variables, then restart the Claude Desktop app to make all twelve tools available.

Yes, you can trigger evaluations directly. Use the `update_monitoring` tool to turn evaluators on or off for specific logs, allowing your agent to manage your testing pipelines straight from the desktop chat interface using the MCP tools.

The MCP server communicates directly with the Humanloop API to fetch and update configurations. When you run `list_prompts`, you get real-time organizational data, ensuring you never work with stale prompt files.

Yes. The `delete_prompt_version` tool allows you to remove unwanted versions from your registry. This keeps your workspace clean without requiring you to log into the cloud platform.

Your Humanloop API keys and prompt configurations are stored locally on your machine and never pass through third-party servers. The MCP sandbox secures your prompt payloads and model generations from external exposure.

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