> ## Documentation Index
> Fetch the complete documentation index at: https://docs.promptjuggler.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Tools

> Give your prompts superpowers: HTTP, scripts, search, MCP, and more.

Tools are functions that a model can call during prompt execution. When the model decides it needs external information or wants to perform an action, it requests a tool call. PromptJuggler executes the tool, feeds the result back, and the model continues – potentially requesting more tools in the same run, across as many rounds as the conversation needs.

## Attaching tools

Open a prompt’s configuration toolbar, click **Tools**, and add as many as you need. Each tool type has its own configuration. You can mix types freely – a prompt can have an HTTP call, a knowledge base search, and an MCP server tool all attached at once.

Every tool has a **name**, a **description** (which tells the model what the tool does and when to use it), and a **fail-fast** toggle. When on, a failed tool call fails the entire prompt run. When off, the error is fed back to the model so it can try a different approach.

## Tool types

<CardGroup cols={2}>
  <Card title="Prompt & Workflow" icon="layers" href="/tools/prompt-and-workflow">
    Call another prompt or trigger a workflow as a tool. Turtles all the way down.
  </Card>

  <Card title="Knowledge Search" icon="search" href="/tools/knowledge-search">
    Search a knowledge base for relevant context.
  </Card>

  <Card title="HTTP Call" icon="globe" href="/tools/http-call">
    Make HTTP requests to external APIs.
  </Card>

  <Card title="Script" icon="code" href="/tools/script">
    Run custom code in a secure sandbox.
  </Card>

  <Card title="Web Search" icon="search" href="/tools/web-search">
    Search the web for current information.
  </Card>

  <Card title="MCP" icon="plug" href="/tools/mcp">
    Connect to Model Context Protocol servers.
  </Card>
</CardGroup>

## How tools work in workflows

When a prompt with tools runs inside a workflow, the tools execute as part of that prompt node’s run. Tool results are internal to the prompt – they feed back into the model’s reasoning but don’t flow through the workflow’s edges. The workflow only sees the prompt’s final output.

If you want a tool’s result to be available to other nodes, use a dedicated node type instead: a [KB Search node](/workflow-nodes/knowledge-search), a [Script node](/workflow-nodes/script), or wire the data through explicitly.