ClaudeChatGPTPerplexityGeminiMicrosoft CopilotRaycastMeta AIGrokZ.aiQwenKimi
DeepSeekMistralCursorVS CodeWindsurfJetBrainsClineLovableVercel AI SDKLangChain

Use Humanloop with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Manage, version, and deploy LLM prompts directly from your AI agent using the Humanloop API.

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 · 12 capabilities

The complete Humanloop capability set.

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

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 12 available through Humanloop.

  1. 01

    Delete prompt version

    Remove a specific version of a prompt

  2. 02

    Deploy prompt

    G., production, staging). Set a specific version as the active deployment for an environment

  3. 03

    List prompt environments

    List all environments and their currently deployed versions for a prompt

  4. 04

    List prompts

    Retrieve a list of all prompts in your organization

Capability set02 / 03

05-08

4 capabilities in this set.

Part of 12 available through Humanloop.

  1. 05

    Remove deployment

    Remove a prompt version from an environment

  2. 06

    Update monitoring

    Activate or deactivate Evaluators for monitoring logs within a prompt

  3. 07

    Update prompt version

    Update the name or description of a specific prompt version

  4. 08

    List prompt versions

    Get all versions associated with a specific prompt

Capability set03 / 03

09-12

4 capabilities in this set.

Part of 12 available through Humanloop.

  1. 09

    Call prompt stream

    Execute a prompt and stream the response

  2. 10

    Get prompt

    Retrieve details for a specific prompt by ID

  3. 11

    Log to prompt

    Record a model generation (log) associated with a specific prompt

  4. 12

    Upsert prompt

    Create or update a prompt configuration

Observed, not estimated

931ms average. Fast in production.

Humanloop is checked daily against the live service.

Daily averagePeak 1069ms
Aug 29Today
Fastest day
858ms
Slowest day
1069ms
14-day trend
Improving-20%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 12 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 Humanloop, so you can see the experience inside your AI.

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

Humanloop Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_SDhmK5J7LYd6XJCbZRuzCR6WIRna9REWi8m4RQ2M/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 — Humanloop capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "humanloop-llm-prompt-management-api-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_SDhmK5J7LYd6XJCbZRuzCR6WIRna9REWi8m4RQ2M/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 Humanloop owners ask.

  • 01

    Can I see the full version history of a specific prompt?

    Yes! Use the list_prompt_versions capability with the Prompt ID. It will return all historical versions, allowing you to track changes and metadata over time.

  • 02

    How do I deploy a prompt version to a specific environment like production?

    You can use the deploy_prompt capability. Provide the Prompt ID and the Environment ID to set that specific version as the active deployment for that environment.

  • 03

    Is it possible to record model outputs for later evaluation?

    Absolutely. Use the log_to_prompt capability to record a generation, including the prompt path, messages, and output, which can then be used for evaluation in Humanloop.