Skip to main content
Connects a prompt to a Model Context Protocol server, giving the model access to whatever tools that server exposes. MCP is an open standard for extending LLM capabilities through external services – think of it as a universal plug for AI tools.

Configuration

  • Name – identifies this MCP connection
  • URL – the MCP server endpoint. Supports environment variable substitution with ${VAR_NAME} syntax, and prompt inputs can fill in its path or query with {{placeholders}}. A password or a credential query parameter takes its secret from a placeholder, e.g. ?token=${MCP_TOKEN}
  • Auth token – the server’s token, kept as an environment variable and referenced as ${VAR_NAME}, so the secret stays in your workspace settings rather than in the prompt
  • Allowed tools – optionally restrict the model to specific tools from the server by listing their names. Leave empty to allow every tool the server exposes
PromptJuggler connects to the server and offers its tools to the model.

Correlation

Like the HTTP Call tool, MCP requests carry the run and thread IDs so your server can correlate them back to a PromptJuggler run:
  • Run ID – the root run ID, shared across every prompt and workflow in the same run tree, so nested calls all report the same value.
  • Thread ID – the conversation thread ID.
They arrive as the PromptJuggler-RunId and PromptJuggler-Thread request headers.