Prompt Chain

Integrate LLMs with External Tools via MCP

Enables LLMs to interact with external tools via the Model Context Protocol, executing tool calls and integrating results back into conversations.

Works with anthropic

90
Spark score
out of 100
Updated 17 days ago
Version 1.0.0
Models

Add to Favorites

Why it matters

Connect large language models like Claude to external tools and services using the Model Context Protocol. This asset enables LLMs to leverage tool outputs and integrate them back into conversations for more dynamic interactions.

Outcomes

What it gets done

01

Wire Anthropic's Claude to an MCP server.

02

Expose MCP server tools to the LLM.

03

Execute tool_use blocks emitted by the model.

04

Feed tool results back into the conversation.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/pfoo-mcp | bash

Capabilities

What this chain does

Chatbot

Handles multi-turn conversations within a defined domain.

Extract

Pulls structured data fields from unstructured text.

Summarize

Condenses long documents or threads into key takeaways.

Overview

Mcp

What it does

This example wires Claude up to a [Model Context Protocol](https://modelcontextprotocol.io) server through the Anthropic Messages provider. Promptfoo exposes the MCP server's tools to Claude, executes any `tool_use` blocks the model emits, and feeds the `tool_result` back into the conversation until Claude produces a final reply.

Source README

This example wires Claude up to a Model Context Protocol server through the Anthropic Messages provider. Promptfoo exposes the MCP server's tools to Claude, executes any tool_use blocks the model emits, and feeds the tool_result back into the conversation until Claude produces a final reply.

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.